diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/mlc-chat-config.json b/mlc-chat-config.json new file mode 100644 index 0000000000000000000000000000000000000000..683face07cf172dd94a09ada0fcc18e2a34d778d --- /dev/null +++ b/mlc-chat-config.json @@ -0,0 +1,83 @@ +{ + "version": "0.1.0", + "model_type": "gemma2", + "quantization": "q4f32_1", + "model_config": { + "hidden_size": 3584, + "intermediate_size": 14336, + "attention_bias": false, + "num_attention_heads": 16, + "num_key_value_heads": 8, + "head_dim": 256, + "num_hidden_layers": 42, + "rms_norm_eps": 1e-06, + "vocab_size": 256000, + "hidden_activation": "gelu_pytorch_tanh", + "position_embedding_base": 10000.0, + "context_window_size": 4096, + "prefill_chunk_size": 2048, + "tensor_parallel_shards": 1, + "max_batch_size": 80, + "attn_logit_softcapping": 50.0, + "final_logit_softcapping": 30.0, + "query_pre_attn_scalar": 256, + "sliding_window": 4096 + }, + "vocab_size": 256000, + "context_window_size": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 2048, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.0, + "top_p": 1.0, + "tokenizer_files": [ + "tokenizer.model", + "tokenizer.json", + "tokenizer_config.json" + ], + "tokenizer_info": { + "token_postproc_method": "byte_fallback", + "prepend_space_in_encode": false, + "strip_space_in_decode": false + }, + "conv_template": { + "name": "gemma_instruction", + "system_template": "{system_message}", + "system_message": "", + "system_prefix_token_ids": [ + 2 + ], + "add_role_after_system_message": true, + "roles": { + "user": "user", + "assistant": "model" + }, + "role_templates": { + "user": "{user_message}", + "assistant": "{assistant_message}", + "tool": "{tool_message}" + }, + "messages": [], + "seps": [ + "\n" + ], + "role_content_sep": "\n", + "role_empty_sep": "\n", + "stop_str": [ + "" + ], + "stop_token_ids": [ + 1, + 107 + ], + "function_string": "", + "use_function_calling": false + }, + "pad_token_id": 0, + "bos_token_id": 2, + "eos_token_id": 1 +} \ No newline at end of file diff --git a/ndarray-cache-b16.json b/ndarray-cache-b16.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1410e6855bd543dd957c719a615fa87f0e6bee --- /dev/null +++ b/ndarray-cache-b16.json @@ -0,0 +1,6441 @@ +{ + "metadata": { + "ParamSize": 507, + "ParamBytes": 5778110464.0, + "BitsPerParam": 5.001769564193918 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 458752000, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 256000, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 458752000, + "byteOffset": 0 + } + ], + "md5sum": "68df25fa1342688826727d9b81aada60" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 57344000, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 256000, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 57344000, + "byteOffset": 0 + } + ], + "md5sum": "62db109c2620840d659e88bd51ac06a7" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "2ce9aa5d3be6bd767f4285fc97a81b38" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 28908544, + "records": [ + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 7168 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 25697280 + } + ], + "md5sum": "35ce5801e52b514eb4600d7653865d52" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b895e10fd6c703501aeb3549dbfcaa27" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.0.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.0.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "0ecf89e9f2918ce6d066466ae30579f6" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "0d5d05afd0971640c4b390dee7c5a09b" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.1.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.1.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "e7eb819bc435bbc8c3b29fb9ad68f794" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "8f0dc5cb40371d0819ba9ace4b6e92f4" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "ca010b2e386b2e972a5c28b85180307d" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "d667049656fba38d6b8b5096c298178d" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.2.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.2.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "6155ba47425758672340543b98030b9a" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "cddec89379a548546fdac5f82381f891" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.3.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.3.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "7cbd4b81fd47c661d1c0c9481e2927a1" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "2c573bd884b12c0c03ac855ba5a7350d" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "578ae41fc50770a5e06f43fa0325bf75" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "c780e0b247403f41e5eee47974a92015" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.4.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.4.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "baf2fec30cd33ba56d9693e9eab17a4d" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "892bab49a36d92c1031754e047f608ff" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.5.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.5.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "cf87272ed7fec8c4e88663d4e8f0ac80" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "1dca2c5fbcccc8734c16293f783bd5e6" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "6a6924876cb2fa705e421557f04d5dce" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "b29546ee471d1f77aaec9894c08bbe8b" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 31216640, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.6.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.6.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + } + ], + "md5sum": "0f9b606fc7e3db3d61217722c5da3225" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b6443eaa80de2f56a20059b081282993" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 31202304, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6422528 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21102592 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22937600 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30277632 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31195136 + } + ], + "md5sum": "365069e61f0fb2ded00d7e7822750538" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "3698a760587b75bdd3441934d5ef9b83" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.10.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.10.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "03c08602a997c2c1d8e219ac3724077e" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "aeb4d1b2641f4a73ad73ab5f4785a3d1" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "0b3be7810b964c26bbc3ad648a408089" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "5d4d4d54ffc994cb91df6383bdc9ca60" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.11.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.11.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "206da69954060f871914cd5661bde2f7" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "6b0ea2f3329444c8f91cd4534ec6ea84" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.12.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.12.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "013a613618727c71f72c8a4c54612029" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "98b55fccfb2c837039d7e680a202619a" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "5006ccd904cbd378320cdad44b4edb15" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "2bdff6474fa98f5eff865e7a604ee287" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.13.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.13.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "238a58591d0330517102fe2598216efd" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "513ec025d40fbdda639a7c6a1a8689a7" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.14.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.14.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "6e4f02de42a39c682b75a6e4670e8d96" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "3012095e53f5cad52067a45feb9629e2" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "2cbc9cfa779cda4be852136b0752042b" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "2e3959cf0c21939da23e697576be091b" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.15.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.15.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "a4948f3fa9e4ff506e6632306397fbda" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "7c769c0de959c08cc4c0f936527dfe49" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.16.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.16.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "5d8fcaea14ec5a25d60c43234231cb9f" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "970bd59740aa7c94d1bb83c6273062a1" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "e692e977ee5843dd21648c7ec318f81a" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "f12f24feac4e04f3d638f069f72dcb7e" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.17.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.17.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "6a00b4e0321daaccd8fe38728aeb1626" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "9d8df06b6ed844f866aae8bc95c05403" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.18.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.18.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "580702b458fbf2c66b0649429d181139" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "65256683d1a990dbbc54a557e1f8b100" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "9b4ac9d63138f4f02465e7d063f112f9" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 31216640, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.19.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.19.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + } + ], + "md5sum": "5a4f11be007a2d584e4241dbf9db91d3" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b180c4c58a72bb137a206b65477c6275" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "2a00510af50b930b3025e50a9fd8d972" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "2908f189cd961cb079fa0fd030732ce0" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 31230976, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 14680064 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 16515072 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 23855104 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 24772608 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 24779776 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 27991040 + }, + { + "name": "model.layers.7.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 27998208 + }, + { + "name": "model.layers.7.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 28005376 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 28012544 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 28019712 + } + ], + "md5sum": "09c2f28fdbb7657e590bb375601909ee" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "dc773cb1b389e1f14d4f59a9ff6399c9" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.8.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.8.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "70b202e03e83057f2c745444357a5a7f" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "994c7b5c04c90cc59f5ed27bf0375213" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.9.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.9.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "86b8efb8d4dfd62344b331a01fb2dc6e" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "5c0b1f89fe8f61439d09fb7a6052cf47" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "3f78ffb34903269c9edfe7599b33d1a7" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 32141312, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.20.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.20.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6444032 + }, + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 6451200 + } + ], + "md5sum": "d0d7e07d958eb09c5bfe777c2428a8c1" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "e34008bc5565c235905cf244bb379946" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.21.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.21.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "4f4ceffbed3373980deef8b502d5d445" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "266ee85d2cc3b18e84c6a5efebff4d4c" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "8b8248c1854b667cf83e06c9f1c655f1" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "17a5e22b5686db74e83c8d7b52653842" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.22.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.22.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "6ec75209b93b015a34b63b418df8a4ce" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "e6420e6737acb1e781aa5879b792ca9b" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.23.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.23.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "72b8c76efff32a86970c814b257aa7da" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "d08548f1c34939ed857e9a8cf083cb08" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "dfc5410ea7b789c776585dc6f1fbad7a" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "0e8ea7158657b34ffa84e4578c617018" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.24.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.24.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "b8a0f22b69bbfa870d0823ecbfb5c381" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "f3f96075f77043c188bcdfdd5ab4c09a" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.25.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.25.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "fe995385520a7aa11d7377d2b1bec6af" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "570f89f7806866789f31444ad2f54671" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "66f7c62b1a66da56144b186a403797e0" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b6be9d4cce739f05a4b6dbbf55bdab17" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.26.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.26.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "b21bb7713334a3930c139193eaa65c2e" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "c40601292bc1a4f07951d79bc652f940" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.27.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.27.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "64d28e280c7684c4a156f64ccb3e5fb5" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "9dfb69aabbd2548ee3a9851f70a04bfc" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "6f572d5a628ff99fd3c7fe784208ca20" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "f7cbe8e7e730722e1c6acbe39ddad1a2" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.28.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.28.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "4be53b811c36e461d00d5ab4d7661242" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "5d1ec40ea4678edc54fc027a0029a400" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.29.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.29.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "850b3d01c0aa023ba273073488b890e8" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "37d68011b4215b0321963eb95ffba4bc" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "fa11ee80afa2233701d3466f3d498f17" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "8fc6c589b7a147222eef93913e27e3bd" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.30.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.30.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "a9a043b844c81aea8a94b4a04dc94bd7" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "5c35d6761f4727a0647650424ea4b43a" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.31.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.31.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "c7ac7f61d87c77b792800fe5d212809d" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "ff2bf01fed1f3b122fe4c086709bc3e9" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "bdb0b25d02e1be271fc996114e82eaa7" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 32119808, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 917504 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 7340032 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 22020096 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 23855104 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 31195136 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 32112640 + } + ], + "md5sum": "a1228e9784d91499736acf1a523e5ac2" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "3f16b96789fafda302c83b8ca7160285" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 32141312, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 3211264 + }, + { + "name": "model.layers.32.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 3218432 + }, + { + "name": "model.layers.32.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 3225600 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 3232768 + }, + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 3239936 + }, + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 28930048 + } + ], + "md5sum": "73ee12188282bf87d2b57fed83b7b71d" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "502e0ce8edbc26192adef3f575d718cc" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.33.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.33.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "a99a58146774554daf944b9111a98795" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "7938b71c0edd956289f399bf3c4b044c" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.34.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.34.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "3d4c12c3a24f08c625dc9102f2905173" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "e69be59e834818ab7a4f400d85b2dc5c" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "b863d3768be4e5e8f2749df3c60df6c4" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "d1e7a7482ab1ced94ea3d560aad0a904" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.35.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.35.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "37c4cb17237e3de9565478c705bdbd25" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "4e7c67ebefd3ae03ee61e04ffdb2ffb6" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.36.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.36.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "6c2269178af6814ae92c23bf8f3041ec" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "30087f352a41e342f9254e586b8d7f02" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "ce7fe17bf7e5b8e88f9727d323822b30" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "ea9d094750ba46dd4546e022e310c33c" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.37.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.37.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "7fa4d132a51ea0c53e4ec4695a5f5f4e" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "143e1d601b849d1423fee1af7ed02f0a" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.38.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.38.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "04592ea5b02b91f6281c1ce53de32332" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "1ac0635ea300466480ea00f317e77c24" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "a75e64102d0f14812bcf475a48d251d1" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "05367ec77d26ce75cd68225830f629af" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.39.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.39.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "610f946abe9fc50b624ad4cd88b7128b" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "a1aafd9fc507bba0f6ce9f068844230b" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.40.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.40.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "fd639250933e1941b9a0e933fd1d3ecd" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "9a090199ab848258427d1db0d1093d83" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "fd9ebb26d478ed528d3172ae1a8941d4" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.41.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.41.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.norm.weight", + "shape": [ + 3584 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "16cf483c0bb9f243d84d4b12b3a421af" + } + ] +} \ No newline at end of file diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..2955c8da2d8d7c20614d07f005004e75d3ec7b3d --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,6441 @@ +{ + "metadata": { + "ParamSize": 507, + "ParamBytes": 5778110464.0, + "BitsPerParam": 5.001769564193918 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 458752000, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 256000, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 458752000, + "byteOffset": 0 + } + ], + "md5sum": "68df25fa1342688826727d9b81aada60" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 57344000, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 256000, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 57344000, + "byteOffset": 0 + } + ], + "md5sum": "62db109c2620840d659e88bd51ac06a7" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "2ce9aa5d3be6bd767f4285fc97a81b38" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 28908544, + "records": [ + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 7168 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 25697280 + } + ], + "md5sum": "35ce5801e52b514eb4600d7653865d52" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b895e10fd6c703501aeb3549dbfcaa27" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.0.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.0.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "0ecf89e9f2918ce6d066466ae30579f6" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "0d5d05afd0971640c4b390dee7c5a09b" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.1.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.1.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "e7eb819bc435bbc8c3b29fb9ad68f794" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "8f0dc5cb40371d0819ba9ace4b6e92f4" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "ca010b2e386b2e972a5c28b85180307d" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "d667049656fba38d6b8b5096c298178d" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.2.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.2.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "6155ba47425758672340543b98030b9a" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "cddec89379a548546fdac5f82381f891" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.3.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.3.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "7cbd4b81fd47c661d1c0c9481e2927a1" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "2c573bd884b12c0c03ac855ba5a7350d" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "578ae41fc50770a5e06f43fa0325bf75" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "c780e0b247403f41e5eee47974a92015" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.4.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.4.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "baf2fec30cd33ba56d9693e9eab17a4d" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "892bab49a36d92c1031754e047f608ff" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.5.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.5.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "cf87272ed7fec8c4e88663d4e8f0ac80" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "1dca2c5fbcccc8734c16293f783bd5e6" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "6a6924876cb2fa705e421557f04d5dce" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "b29546ee471d1f77aaec9894c08bbe8b" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 31216640, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.6.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.6.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + } + ], + "md5sum": "0f9b606fc7e3db3d61217722c5da3225" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b6443eaa80de2f56a20059b081282993" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 31202304, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6422528 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21102592 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22937600 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30277632 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31195136 + } + ], + "md5sum": "365069e61f0fb2ded00d7e7822750538" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "3698a760587b75bdd3441934d5ef9b83" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.10.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.10.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "03c08602a997c2c1d8e219ac3724077e" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "aeb4d1b2641f4a73ad73ab5f4785a3d1" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "0b3be7810b964c26bbc3ad648a408089" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "5d4d4d54ffc994cb91df6383bdc9ca60" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.11.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.11.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "206da69954060f871914cd5661bde2f7" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "6b0ea2f3329444c8f91cd4534ec6ea84" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.12.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.12.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "013a613618727c71f72c8a4c54612029" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "98b55fccfb2c837039d7e680a202619a" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "5006ccd904cbd378320cdad44b4edb15" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "2bdff6474fa98f5eff865e7a604ee287" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.13.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.13.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "238a58591d0330517102fe2598216efd" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "513ec025d40fbdda639a7c6a1a8689a7" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.14.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.14.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "6e4f02de42a39c682b75a6e4670e8d96" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "3012095e53f5cad52067a45feb9629e2" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "2cbc9cfa779cda4be852136b0752042b" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "2e3959cf0c21939da23e697576be091b" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.15.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.15.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "a4948f3fa9e4ff506e6632306397fbda" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "7c769c0de959c08cc4c0f936527dfe49" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.16.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.16.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "5d8fcaea14ec5a25d60c43234231cb9f" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "970bd59740aa7c94d1bb83c6273062a1" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "e692e977ee5843dd21648c7ec318f81a" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "f12f24feac4e04f3d638f069f72dcb7e" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.17.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.17.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "6a00b4e0321daaccd8fe38728aeb1626" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "9d8df06b6ed844f866aae8bc95c05403" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.18.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.18.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "580702b458fbf2c66b0649429d181139" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "65256683d1a990dbbc54a557e1f8b100" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "9b4ac9d63138f4f02465e7d063f112f9" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 31216640, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.19.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.19.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + } + ], + "md5sum": "5a4f11be007a2d584e4241dbf9db91d3" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b180c4c58a72bb137a206b65477c6275" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "2a00510af50b930b3025e50a9fd8d972" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "2908f189cd961cb079fa0fd030732ce0" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 31230976, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 14680064 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 16515072 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 23855104 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 24772608 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 24779776 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 27991040 + }, + { + "name": "model.layers.7.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 27998208 + }, + { + "name": "model.layers.7.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 28005376 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 28012544 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 28019712 + } + ], + "md5sum": "09c2f28fdbb7657e590bb375601909ee" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "dc773cb1b389e1f14d4f59a9ff6399c9" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.8.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.8.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "70b202e03e83057f2c745444357a5a7f" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "994c7b5c04c90cc59f5ed27bf0375213" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.9.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.9.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "86b8efb8d4dfd62344b331a01fb2dc6e" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "5c0b1f89fe8f61439d09fb7a6052cf47" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "3f78ffb34903269c9edfe7599b33d1a7" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 32141312, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.20.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.20.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6444032 + }, + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 6451200 + } + ], + "md5sum": "d0d7e07d958eb09c5bfe777c2428a8c1" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "e34008bc5565c235905cf244bb379946" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.21.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.21.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "4f4ceffbed3373980deef8b502d5d445" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "266ee85d2cc3b18e84c6a5efebff4d4c" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "8b8248c1854b667cf83e06c9f1c655f1" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "17a5e22b5686db74e83c8d7b52653842" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.22.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.22.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "6ec75209b93b015a34b63b418df8a4ce" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "e6420e6737acb1e781aa5879b792ca9b" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.23.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.23.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "72b8c76efff32a86970c814b257aa7da" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "d08548f1c34939ed857e9a8cf083cb08" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "dfc5410ea7b789c776585dc6f1fbad7a" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "0e8ea7158657b34ffa84e4578c617018" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.24.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.24.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "b8a0f22b69bbfa870d0823ecbfb5c381" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "f3f96075f77043c188bcdfdd5ab4c09a" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.25.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.25.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "fe995385520a7aa11d7377d2b1bec6af" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "570f89f7806866789f31444ad2f54671" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "66f7c62b1a66da56144b186a403797e0" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "b6be9d4cce739f05a4b6dbbf55bdab17" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.26.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.26.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "b21bb7713334a3930c139193eaa65c2e" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "c40601292bc1a4f07951d79bc652f940" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.27.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.27.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "64d28e280c7684c4a156f64ccb3e5fb5" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "9dfb69aabbd2548ee3a9851f70a04bfc" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "6f572d5a628ff99fd3c7fe784208ca20" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "f7cbe8e7e730722e1c6acbe39ddad1a2" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.28.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.28.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "4be53b811c36e461d00d5ab4d7661242" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "5d1ec40ea4678edc54fc027a0029a400" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.29.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.29.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "850b3d01c0aa023ba273073488b890e8" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "37d68011b4215b0321963eb95ffba4bc" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "fa11ee80afa2233701d3466f3d498f17" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "8fc6c589b7a147222eef93913e27e3bd" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.30.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.30.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "a9a043b844c81aea8a94b4a04dc94bd7" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "5c35d6761f4727a0647650424ea4b43a" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.31.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.31.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "c7ac7f61d87c77b792800fe5d212809d" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "ff2bf01fed1f3b122fe4c086709bc3e9" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "bdb0b25d02e1be271fc996114e82eaa7" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 32119808, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 917504 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 7340032 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 22020096 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 23855104 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 31195136 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 32112640 + } + ], + "md5sum": "a1228e9784d91499736acf1a523e5ac2" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "3f16b96789fafda302c83b8ca7160285" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 32141312, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 3211264 + }, + { + "name": "model.layers.32.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 3218432 + }, + { + "name": "model.layers.32.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 3225600 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 3232768 + }, + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 3239936 + }, + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 28930048 + } + ], + "md5sum": "73ee12188282bf87d2b57fed83b7b71d" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "502e0ce8edbc26192adef3f575d718cc" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.33.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.33.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "a99a58146774554daf944b9111a98795" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "7938b71c0edd956289f399bf3c4b044c" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.34.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.34.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "3d4c12c3a24f08c625dc9102f2905173" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "e69be59e834818ab7a4f400d85b2dc5c" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "b863d3768be4e5e8f2749df3c60df6c4" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "d1e7a7482ab1ced94ea3d560aad0a904" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.35.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.35.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "37c4cb17237e3de9565478c705bdbd25" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "4e7c67ebefd3ae03ee61e04ffdb2ffb6" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.36.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.36.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "6c2269178af6814ae92c23bf8f3041ec" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "30087f352a41e342f9254e586b8d7f02" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "ce7fe17bf7e5b8e88f9727d323822b30" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "ea9d094750ba46dd4546e022e310c33c" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.37.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.37.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "7fa4d132a51ea0c53e4ec4695a5f5f4e" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "143e1d601b849d1423fee1af7ed02f0a" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.38.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.38.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "04592ea5b02b91f6281c1ce53de32332" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "1ac0635ea300466480ea00f317e77c24" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "a75e64102d0f14812bcf475a48d251d1" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 25690112, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 0 + } + ], + "md5sum": "05367ec77d26ce75cd68225830f629af" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.39.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.39.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "610f946abe9fc50b624ad4cd88b7128b" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "a1aafd9fc507bba0f6ce9f068844230b" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 33510400, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 0 + }, + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 3211264 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9633792 + }, + { + "name": "model.layers.40.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9640960 + }, + { + "name": "model.layers.40.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 9648128 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9655296 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 24335360 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 26170368 + } + ], + "md5sum": "fd639250933e1941b9a0e933fd1d3ecd" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 51380224, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 51380224, + "byteOffset": 0 + } + ], + "md5sum": "9a090199ab848258427d1db0d1093d83" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 29826048, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 0 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 917504 + }, + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 3584, + 1792 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25690112, + "byteOffset": 924672 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 3584, + 448 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 3211264, + "byteOffset": 26614784 + } + ], + "md5sum": "fd9ebb26d478ed528d3172ae1a8941d4" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 31223808, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 6422528, + "byteOffset": 0 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6422528 + }, + { + "name": "model.layers.41.post_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6429696 + }, + { + "name": "model.layers.41.pre_feedforward_layernorm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 6436864 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 8192, + 448 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 6444032 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 8192, + 112 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1835008, + "byteOffset": 21124096 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 3584, + 512 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 22959104 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 3584, + 128 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 917504, + "byteOffset": 30299136 + }, + { + "name": "model.norm.weight", + "shape": [ + 3584 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 7168, + "byteOffset": 31216640 + } + ], + "md5sum": "16cf483c0bb9f243d84d4b12b3a421af" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..f18fe47cbb5c29606bcd1edad632b4038f453bc5 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4d29ba7486f30331d513a1c4de834c358153a8c1330a598e8eaa3b6d85de90 +size 458752000 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..afd1e2c168adf678a179821390508f66c5afe72d --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42a3e721c1e97748d45ac551301196e230bdce463f52acb66be2cc7fd3296248 +size 57344000 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..12f969c75fc6b23e1ac0452f64a8f25bccba648a --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77cb98bfa068d53c54cbce1f1734a96b575ffd07f6f01b55990299f08d487d42 +size 25690112 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..c464aee08ca4ca4336a0df7421611d17c2b838ae --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1a7666b94720273156571ae3ac6e455e2601dd73a5de90ff42176e310f2c78 +size 32119808 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b52eafb41330890484f29089401707da7f88df4 --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704e609a00e03d84fecc1e959f10f952a9b0f5ebeab90e69600342b71d90f739 +size 51380224 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..27a509a471178a94693e114140389ba9a6595ba0 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf80c20c73596302876cf689393ce1c1b11c057ee32e04e0a08f83cd36b60cd +size 32141312 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..babc723a72b639c0959f6873828141e52c412ece --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb4f8a606daf12c0d24d7984ce4f3d5dd1f1bf91e4e01ece771ecc846503c89 +size 25690112 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..aec85ae928eef3afcf9753f9c02fdfbdab80e952 --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d9788ed20b7376cb95aae49e3e17bf136a0ea6ee226d41bc2592fa48005570 +size 31223808 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a108fbd27507a2c86d9e7dfe83ae6973b889109 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6e7dca51d6b089c8d7e9a9feca374b3d0ced403f7c0076c85abfebdac42673 +size 51380224 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..2c5305cccc5d1fe11946dcc1aea618ff88243bc2 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f8ce9a43659690247dea3b40b01e051907abf82b05654cf21d2e02bf8b306b +size 33510400 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..41ee4e1f7d03e786d07349751be9f8970b82c732 --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d691104159ecf1b23329628088d05a6166354247fd436c989e2f9b4270daa88 +size 51380224 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..416139445caf4e3eb683f039b2b721a2e4cf20e2 --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101dcd44db0754a9d467b90b5f44320e77e4624e25b7cdbf9ef021cb3f38db15 +size 29826048 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..b8bac2a9434b15d3a10f3aaec8692d6d9318ce2c --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b11eb1e35c64963d1bb304ab39e41da661b2013b5bc1b64fd13b36d817e7ced0 +size 25690112 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c1550398f350e263c998bb879a1eb1547755d09 --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9ea6fc6d57c40b89be56fefd0f562821976f3776dd4bf649de4ad707d7dc28e +size 31223808 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..d2bcdb4ff914642503ba6dad3054603b8c8d5923 --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018b422643cabe2bc0f88e82a3b975c1bf2b537cee6c769d981f61902d606d2e +size 31223808 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..00738bd0730d77545015a2043f45e297f0f6cc87 --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d280cf392451afe0aa19d2ebf2c3a8bdd62f6a0af8bc571ed0a07f78b91a5cb5 +size 51380224 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..bbd7b1170a0989f33044a9f9476ec49b0403f79a --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf06d44cfc2a9c0b667f99b7a1b17777868f6bd0d21ed5c27ad83a3d7804692c +size 33510400 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..54d322a6ab6446cf60e8cfc62b6e3294d0923136 --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0e6548a7ef69114a1a5d6cc101e723a0d6573ee7177fd404a87fdc94a86134 +size 51380224 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d326ae4363572c9a6e4f7a7c495a7dd62ee3075 --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:023c37b12f242b4404823d6a37d65301691c8ccb40e32c28fa3ad97255452aea +size 29826048 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..a3b372eddeac78aa288e838625ced81d97c9ac5c --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41591de0dc90ffdc644df8e24cbf55b63c1f95c86a1a14ab9ed96c49b1cd44d6 +size 25690112 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..6f8d765bb5a19dc253f8a3fbc303274db60bda86 --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7042f75ee430e8cdf6559ec73dd3e422f91231f76ad07b83a45dd892f61f626b +size 31223808 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..80d53cec7595cb867b5677805b4295a09e82086a --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5076461f7492aa78f6589fecae5c33eb2dca870c2b92b8ce64c1afa35e518a66 +size 51380224 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..b366bd3b0cf16c563a2d8fde85a4b5a4a75be333 --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2024cfd8327898a52b7a456e9d947cbf6a995fd494ad370c090312657aa03287 +size 33510400 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e69fcfc688db8d33abb318fa519742141226df8 --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6295faeeabdcd026965a9215313e30a63b684f3745613b018286d0c8a2d1854c +size 51380224 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..d04c5f15bfdb88ba902fa6527ced48dfdda3df49 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec35023927fec64909134f50de86f7ac865d70e6c6c2b693d71a25b29228c9d +size 51380224 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..f28566b4dd86cde76c8b064947285f2e1945e254 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f65efabc1fffce3a0d782b385a4489f105112f2d49fef99ef1e68e873948736d +size 29826048 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..70a52b3019d3f2f357a5a0985d843ce3048222b8 --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e7af159f7c5fa957801597f6fde63ce1f5c37a28fa03545acb5b0049331db9 +size 25690112 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..1be8c311a64cb811e26e80be1de6b31a6b4e4ea2 --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76efb42ccf023f547634684b50bed9d4b6cee511e22abc8641a4952e36b70d7 +size 31223808 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..ebfd8eab06cbb29589229decd956ad3bf52e07c9 --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f538fc540a6fa1e218967200528e8f1e5064ecf4eb246607d6a0687fc4c8cf +size 51380224 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..7471c237a78520a0a60661bbf843fc45bb8b5a0a --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb63802352f47c73f5609a7b8dd6e6d35de19c22abc745d91b5f83117007a97e +size 33510400 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..9497a3a48a390df3ef18da6b2a27da6e6da2bcbd --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b0f6d46f057ea76cb0d9aa0324050f49c6d021d4b6edc45eecfdde2feb0b1e +size 51380224 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..c395eee5239cd0951e909a27dd22e61fb7e4bc15 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78d4ed5f9a972d78598bc3799fa2afdfc263397377a24029c27ffb8937825f4 +size 29826048 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..7e46777714de69b031aa2d9e19742bafb8ad1567 --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ee2aca41a32c3c72d92fa59601cab1b213afa81bf07c63afdf3ecc4c3da3f7 +size 31223808 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..59bbeb058032743330351e09c83d9d8a8f89aac1 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78d60f56c2070277b3c6913ca3af506ea72f89cc2409a9ebd66078d8d8f1c45 +size 33510400 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b183f8a6daa4a474760b661833f6f646a7f3c6e --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f60323a8b986d3e65320192a335618685475eb419403df6592f3d0e3e1966d8 +size 51380224 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..23dfdd917580d0f630aa3d11a4a82cf81007ad9a --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e83579ec062eb7c5f556f64ded0fc3421408f817a59d2b85f5c12edaec0f6272 +size 29826048 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..86e9c0c766ea24de0866f7e9ddf355d202ecd23b --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bfaef6396764ad77eb80a028f27a40f3bc231a9ac7ab8480d895096bcf8279 +size 25690112 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ac0acf5a6fed25954c1e6d53163e020a1ac1a1b --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5f2a31811926796bcb6de62654c84020f2a5d5980b4aa5c0733571cccbb4f4 +size 31223808 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..e2010cb6e0ab04dee12e3827c5b9ad9912589343 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66428df3a1ba53aa83eb1ca242e4efcc2d31e4cf721861814ba85c980f39bd89 +size 51380224 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..e778bc8c57af6181ffe4f37e53da35f0c1f9b316 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66fdecdb686b85c51021fcb9a9d7589e82f5bb0941a0a516995a980fbf7ae0e9 +size 33510400 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..954d9633e95105e1547728278a4c5133f93630ff --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a49a3b4f1d33cbb4976335d0f6eca4b193da368f536076392996f4d01b64c3 +size 51380224 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b6553c26e1f84638d09796991611583ce292e98 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a87f3aca4382f672f9d4cba887f54dfb2369561396d37643dd98632bb70243 +size 51380224 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..29638146a2f79aa0f4a486fb1ccbe064c0c6db16 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad581472e0d6fcb26dbc7c4e9c0ebf079b9b947f267d8bf3e2a6f9c5e45bf4d +size 29826048 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..b63724110f15953037398213f5911546f2314cfc --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17415c819a52c6c5c37024ca04187e406f981cc98caee10d5a9e3d610d85c9bd +size 51380224 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..96f1e3105ae9af95d35b4e5828d40267b965b037 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece00a59d609581ebe3c75023ab0a2662aa7a94cbd06bc733739930139883911 +size 31216640 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..837413c88791c0479ea60031972c024b677de839 --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b1d7359f90de4ca07fcc27e9668413c0d6f2f28405899f83af119a5509d0a8 +size 25690112 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..d060cf0d7ffa9f166e30caf1c43a6b22e4b57daf --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2069dbfc61cfb7bd8f9cffd082dd54642ff7d61a3e8cbceec83c02ab77be46a +size 31202304 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..26184389552711b2b6a943858243af406c6a2fa7 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21ffd596012fad1e1bd1a97068a69bbf86811d153d883c6c692cf22f48f4c88a +size 51380224 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..e14c2f1c3c03231d943b215993bbc7c287d122f6 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f7fab6533641f2458907d0a21c6e2906a3144f1f68e7e9d0c8f5f76997b498 +size 33510400 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..847b27c81a81e968c1e22ccc6bce299be67882d0 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa520eafc6de9a57d1886d2eb1e6ba20ba43a9b3f7d54b8cb70954db5c572498 +size 51380224 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..71b0fe5c9437f6e7aa1271fade27210542a7cbd9 --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9af94631f84b68c25b78054826bfbddee6cdb9903f8c8a08d9ed6f00d4dfd3f +size 29826048 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..1dce1fe2bd79fbbeb70d6842935ccd56e2ee400b --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4eed67d01842c9a61cd4488a72d826af51a394ca645b31d8564dea158e2f282 +size 28908544 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..e969dbeb2fe7b6ac38e3a80f2baf7dc5e85389e1 --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d334bc922753ac389b7302c6f4ab8461eeb016a03150c440a372120e74af07 +size 25690112 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..c457e4d04ab84676b7366ce406c7327f5f2d389f --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adfafb3cb880be4a64d678a570a5bb2b87012994183840a1c0c77a8029717dd3 +size 31223808 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d1479822290a62c89a0fd7abf63986418f94427 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa87e191407ac6d9c506b526acaf2fcea3d7be91b5cfdc29ad8443698d09695 +size 51380224 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e7cda5dbf391b56839566cfec48a4dfbaf99748 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cad9f2c8ba25c0242d241bdf952ef42e339b9b0e6f5e0d2e4fc5b95e254b7fb +size 33510400 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..daed34a0e89f78fc260c52d7d4f0599019668044 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344395efe6f6515a96bfb2b3b6b912e34910d7cff12d468c308264797b24436b +size 51380224 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..61af7aeab499c136a27f40d072ccd06712f9f07f --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c7ad8e7b6cca41bf161e849600d1217c335dfeb7fe3f8687e2d4e69a947344 +size 29826048 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..132dad86410a6ffe190086d27626438cea273d07 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4230b1ea2c838b2860512a5081626cd75927dea62b4ede0f5ded44a434c39fdb +size 25690112 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..73a4ddc10517c3e3e1d8fee1fa6b9f0c7fa86737 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8efc71db6e4b543f07e17f6199ba7f9137526b83e964b7fa7551a6d960075987 +size 31223808 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..76305749b8d4521da55721338f114bc06d49085a --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdccbe35200212fa39a4bf69575c1231eae58ef4c0b50bab95b257bb738aec0f +size 51380224 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4c4f1aa2ba8e461bc273d47786a82ff2a1b71a7 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c6312f115eeb38ec099e7a1cf163bf0c07dc03a3722c71fe9dcce16b60cc32 +size 33510400 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..0cd55144517b32a57827e6b52e1c14a38a1b9874 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b311801791c4266e349bba98381cf52502bcccdc93baf0bcb6c0cf694fd7a7c +size 25690112 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..939f892125328111a02bc783c11c6b726ee0c026 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36832a8608a5e149d5e530a4ad4ef67a68446a6cfa7cc807db7b4c081dd0b9c9 +size 51380224 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6236de910d4c054e02ea68e5ec9a8f42c1efc3c --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5d714648e11540c6477c55c739387a2130bd7a42204653a64f70f02c82e486e +size 29826048 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..ab1cb3d339413a0e25701e71b729dc6c564bfd90 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de797daa5a44220fe2b154a21bcfa40af33ba73b9c0c878f050d3af832befdcc +size 25690112 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..91f479acdc11d77a3bd07e44c1dd2ca83be3e0fe --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a9eab930e4b9e58881b38e9ff8c0936d7805d64b614839c8263aa879313259 +size 31223808 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d513e7744cccd92895c1103d123f6d24a030498 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92967acd7254666d1c90dca55e299f1ef59f1f7a4d7a63c8ec0c7ab26d7b5cf +size 51380224 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf6be00a3afb8600eccc794e7a8fdab2d5bf05dd --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d7abc0d8ebd21d2c07884281d0fa628d807e3c58de7c9107fe7b451d9be4824 +size 33510400 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd76806a4c263916f5a6f4c731f82f49e7f2f526 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555862d80c731d1833912d267108a9ea5d07908b89c10f3f655ede8ccebb5ffd +size 51380224 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..c870372df116d5a4a6057e0126e2711e4152f926 --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34ae7e724d7224240cdf075628bfcf753b766ab13410b0267ce790a9a70616b +size 29826048 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e81726297a51aca50e3e966a1e852a63a1a4a65 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56574bd1238fae04c40f2de33d75db6a8754945c1ed3d8e3720ada692a298b72 +size 25690112 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..74f0db352d31e5fbb77c637fa49af814c5535f87 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a07c7a48bf5859e265bc52bcd1159e50cb392b8a4f8d052cef10def7d643a19 +size 31223808 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..260c697e5a7889e5ae5fb1d0ebbb045a7a8b2c78 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd975128cb83b6e7bb6d40f8ec818783f93a1796273a39fb6aaebde3339e57f +size 31223808 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..e7bdb18ced215862148c6c4f81491e74f12a148d --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32aead4a4a679baea03d8ffbb936b948ae03509f6945f9626b0f6b4a736b4592 +size 51380224 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c48bb4a64a755724553417a15433b4870e48a5b --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dafd6272dddce9aec33996d789a3f0ee9014857414e678ea2eef66f8d98a0fda +size 33510400 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f280345837f51eb8f55f6ac1c3ea04b3b045d4e --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47d4f3e2290778cd3ea43d0115b2771f131c78b517d70ba9c4faea183b71e50 +size 51380224 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..540a3ed40bd7b89cd97a15246e86eba0928efffc --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f924a1d799568e07482b5435189999675a5c52aa158acd185cb5832391c0a49 +size 29826048 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..efa95c321726a92a8e97bf911a5eded7e29f3215 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a9a6a006911162456899ad6fe7b9845cafae2b02581ffcd54f57d5cb343042 +size 31216640 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b552331c0dee876cd004688e3daa8276c706dc3 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fd89d9ae565b4aaee6e380911ff6306a30397c2c3823c5e7b82081485253b0 +size 25690112 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..c3b432b8c31ba6a57f0d6b9df204b331c9e4e7b8 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7097ab8d9161335cef6971f2556619e6d7eba3b113f48655c0eec555ee4db021 +size 25690112 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..8ec11a22a6610964d87363255384beaf31f0ac1f --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529f98e3a2fd9ba7b3064ab38c814f7ce32f4750b54fb224cd8436bac63d2299 +size 51380224 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..cda2e026bf4672adc13f7905869543d78f65c42f --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6554e145a1ce74dde9e5437cc6ee702cb19052425e3916c2769c1c7391c40cb3 +size 31230976 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0f09342cba8fcaa408fe011d1c345ec8773f739 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4dc7195d9eb7bf57a167407d540bda36fc8f849de8f2f062e2d263079023d8 +size 25690112 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..e23da3975dea9a0ea65d667d97d9bfe59691db00 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c56dee90592c6a283856e434747b7e4b2003e67556f7e8f3236d3dc4dbccf3 +size 51380224 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..462220791ec2b5faff5515856031bf65a5812584 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c608376243126773174b2f0ccda5a245ef3c2e35cdfe1ed34f69e5bfa8ef7d8 +size 31223808 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..ba09ec129d5429fc55683af88d043f6403004988 --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db504971dbccb469eb05d6a31081741337f686b90b0fa4e9e5067dbf59956468 +size 51380224 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..c2c13ee7954da68992b0021a3528db39757aac4a --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c31a2a831165133c5071372c61b6d8193adca0e6b249454fde2d4fc649763772 +size 33510400 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..f399068111afe1978c99c9066038879e75ebb505 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de5042fa57a6750955fa9c0a23453d8fbe5e9f1c7bb7da137cd8bbe00e6ab73 +size 51380224 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..ca68a2f4464859d2f2d739f5e8e7639eec5ddcf7 --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252029ea3b243e52f5e51abbdfc9e06a9edc4a99a58c41562b842dcccba1c3c2 +size 29826048 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..4a77e5782e15790e10be70d0d15eb945e1050ed5 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc412ea690f449ebf70e5b1b9101eb866e18040deda7ca03177c4358530e9e4 +size 32141312 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..cff847fc63cd24c145b6706e94fa2ff707b07584 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917f0157a92e2f94eae61437d881676ccf77b6328dab71a1a7aceda76a9ae756 +size 51380224 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..33318dde27b48bcaf59a6b18501e1ab195f92d54 --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b18b83c03dde009261f73d33a2e4a72d56cd594a0d656a188d928c874786ea +size 33510400 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd708cf5b9c56a4c81ef25860012b68fdceeec9a --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:906d10a82a057bd10ba74b6f1a245ae31d1bb39d000b799cc13baeccbafe1366 +size 51380224 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa295e063cabbd1a01414ecc77a093478681412f --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da20d90e5eecf825882298d42a61282cad7f687087499b42e2b95737ea6fc208 +size 29826048 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..f39ecdd86446651355b3a0386890cfd5aad500fa --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5caaef77d04741f7251ed74bdf96f757266b56a9f38b8a608b24b2dabbd2c397 +size 33510400 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6a22786e8b68ade7df2c3ad92bc5195ada6e6a7 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b76916097242ab689a812136dbdee899c70f642fda850691403ad1a7fce3f4 +size 25690112 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..d193cde4e185166f6b54aec37943f505d7f2f851 --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b34e4da57352686dbffe89663e4e308c097c28f2d400cceb018ed3b5b26f1a8 +size 31223808 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..e396a8365548dccf7c448b16fc200e2be4fbf4ae --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e1fbb8d9cc1b1e087280b6ecfb00fdadb008a84995816c6bb23aa1a5f8aa15 +size 51380224 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..eec620677b9e65ae329fe778183f2f9186c2e89d --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b37730880f0626164d6cf0464b15cf3905e7a25b9499afa4cfb11f23234ad1 +size 33510400 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..21c98d4bf41eea5f841d55e93e719a8663acf2d8 --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3597468c062047ad2d5d39762b3a5d3f756397c4c3dad94ec6871bec5337dc8 +size 51380224 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..98d6563ef063b3641cb8184096b4968a0834a057 --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87a219894cdbdb791197c94be9a1bd757e06ce2e48e7a40e615619b4670868c +size 29826048 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..88c62804e3282d2052a346635025067a5a4d122d --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa21ce89ea5a7e01e7203b15902630b0cf2f1d8e79e9f14531ed9144a8f7a92 +size 25690112 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..f59e56dfcb07683be44a4209fb4a6388b2504c74 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9316d780140b9130fc14b6bfcf3dea1e83df6e92ea553318b4d5d5606aadc1a +size 31223808 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b621ab00c075b40805f730a5f91b4da4b12fa94 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aab99e59149737adc0987d09dedd80d84e7a9491be69e530bad657a5a7287e1 +size 51380224 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..8359745de645908c4bf7cd886355a88784a2437b --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9573b14cf4badad0ae98ef3b34cc4cb6cf6a7e0a52dc077eac60ecced5782ec +size 33510400 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5680290d32bd74edf9e7a69ea74aec5a2768caa --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc378cd701a2b1f4d77d5cc3b2a54f7d8a82fdd74187ecc32234d65b7fd5c3e +size 51380224 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..21aec77e6142c8eca6426b7e8a2dc9946b492d9c --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03df0514e7fdbb6644693d695c4f5d9058920a60431619fa9b859dd2209af53d +size 51380224 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..f5ef91280e0d52271998f724b395be64bf560248 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c74f611dd5137ac9d9d9663545cd1aecc04e9c3d24bbe343e381080d31452dde +size 29826048 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..67541df6827f862f30085e0448cc98830f6e9920 --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c58698edea9f0af07fb5897cf618fe159e7d739ec25f5a8d91e433f62a525777 +size 25690112 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..322f4014e73f22fb7baf0ad4cf807069604aecb1 --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0526639784e191b09785b30e5d50e26a1ca38cfc7357502c1a4ab1852c02b099 +size 31223808 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..eba092eaabf93985ec38a51a544fb3d73da7b7af --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168361f56ff4e22c8976ccaad059d2e32eec046aa9f22d01c69548831cd4b1df +size 51380224 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd7b639f4a6859d8603cf54801101a66e94d0afe --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e45cdec79e6a37e4bc06bcf4e5810ed87f87fc3dc91ac5f2659c339df5125131 +size 33510400 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e41026bb4d0c58f65ae296060110c1e0b3a10bd --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a929a97a57c31d380538eb697f114536cc9554039d009e97c097a17e10e2f9 +size 51380224 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..a64a539f043ddb8e65962eea8a2ed03d15db28a4 --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7f9a3ae998fb5b774e0b6ba57b4bc0a6d9330197375ac73f8651d10784996d +size 29826048 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..523f98a052a6ade2cd03941e912aed4b8afdcc4a --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595624f4e67a52592e017b064b69f116331d817116ae7e55825de44e9f42d8c2 +size 25690112 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..c34934f1e7c5304aa4e332116851c0940231a466 --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177c1b136aa790baa313f1257d7401ac9049a10e89c998f69c55f25173f2db54 +size 31223808 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..504fb79ed36da7d78234b0e33f55f43303e2ad9a --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:200414721b94e55b8a50c80db048155f383ac00ddd86669c781b01a8ae766948 +size 29826048 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..18a6dc01248159172811cd9f3c22aec39506855a --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7acb520ee34dd8fd8346c5a40e9c4135c1b54682dfd3feb824f18c75dc28c197 +size 51380224 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..d2143343145e0b2aa72472a579d1036b7e2987ab --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728ee84d9a847120c6b2e63e5eef7a5e8a537c0c3cb68ad46a75e01b7b6c80bd +size 33510400 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..b03373de6c3e7390dd5fe861ec10209da4e5bcac --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81eb6d6b365ff9146aec1274f206c40e3f0314a12008a035054f709862891819 +size 51380224 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d33010832493911a9f8005038f6867a7d5bc712 --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:979cf8b45303ef58b4dbdf774d06020339077fa30eca895911b3658f7bce24d8 +size 29826048 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d5594cb05e1f760661cbab2e287dce6b5afc4a8 --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9edeacdda028da9f9e39d44d31ad60398eaa715539803b8e5b7a09bbaf059eaa +size 25690112 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..e199b05195818f4f38f9ba13877f1359898f3c17 --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c575ceacaf4fed85387dfaa502286b48c55373cfb9baa8ef96bc089fece6bdc +size 31223808 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..e85469f4ebb74b66d1844599a7d78b7758d7967a --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de768ae34c63d7c3c421033c8b2db5837d0a4c9b08c57e081b596aff3a3dcc99 +size 51380224 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..b73a4735f65273545ef4005ce98205351112d822 --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36650f521ee0cb76b841f7d567d11a5ce0ecff2cd33905b3edc6ab2efd5aee1c +size 33510400 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..e93d6da9afb4b90b28e4e41fb29aea45defcc67b --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b48b9a5d946c18cc6bb18df4884830d6778b381b44aec02186dfc312602073c +size 51380224 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a7c9b73ded19fcb21fb2643266a3a343b5f4efe --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:893f5c9c0cd7a19e6f6bcccf2e782c5a049b246ab5058d9b866f236ffb462142 +size 25690112 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..5771f48b1e9b53a3865929ed27275c483186c9d7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79 +size 17518525 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0e9edce2d1a5e6a5b002865aeade7f475ecf087d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,1757 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "", + "" + ], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}