diff --git "a/ndarray-cache.json" "b/ndarray-cache.json" new file mode 100644--- /dev/null +++ "b/ndarray-cache.json" @@ -0,0 +1,4311 @@ +{ + "metadata": { + "ParamSize": 325, + "ParamBytes": 3631664128.0, + "BitsPerParam": 2.6739310072364444 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 211365888, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 128256, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 211365888, + "byteOffset": 0 + } + ], + "md5sum": "e93ed4e868c432d94a92c0d3bda4217f" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "1edb38f0c88cd75a43c318920c5b4397" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "006b537d79ee00f1c372a4204cd1f6ea" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 29369856, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 128256, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 26420736, + "byteOffset": 0 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 26420736 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 26428928 + } + ], + "md5sum": "a4f9d64272047ddc8cc996e5e1440713" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "3cacd0ee27f986d607f131c5e31622e6" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "a943f4cf628b760b55a17f84c60f865f" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 5914624 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 12664832 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 13508608 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 23633920 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "4b536d32dc6d2be891eda855c084648d" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 211365888, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128256, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 211365888, + "byteOffset": 0 + } + ], + "md5sum": "a2c2c8a2dc7bb0d6e0f150c203c551b8" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 26420736, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128256, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 26420736, + "byteOffset": 0 + } + ], + "md5sum": "5bf2bc9c65d4ce89b26c7a74147d923c" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "e91b2330ab834e9ef783d9015d18076f" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "b19954013a308dec4e1817a9ccf969fd" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 27856896, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.norm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24907776 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24915968 + } + ], + "md5sum": "693c981182887bff0b46b609dbbc2737" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "98cd641c06069a5e972ce732e6042642" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "7750b0825e76b9014353622e40f14f52" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "a1395fa66557cc100e4da2eb8c6f01f0" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "2a1e5f7ed9a3632df5d0f9f1ecd62a12" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "523a190312cfcac2d0c83b6f99cfffb3" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "2fd98bc3fa4b2bb49173e8ba8c33b020" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "3d1e696337ff749ae37545f8d4876b30" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "11fe7d6020ff653ad789b6717d24c9c3" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "5e456f949e0a09c1d38ce9d6cc943878" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "ad04dfbd5233f1d16fcd6fa53474878c" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "e46c50e82b9ee93f975f5f92fecbfb41" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "ae496590182bf199026c7d105a42d5f3" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "f7ce77e5411315d30b6a08d65f043f45" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "85714d5691f0e76203d26b72b3ee439e" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "0594ed3a208c12220830da6ae4f0204c" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "3c3786d029db0d7efedef1ba1bd4387d" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "e35b1e0e7a2d15ed2304bf074cfaef03" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "800c36144c4d0a2dfa6179e13e0445cb" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "a8b7c61f971b51226f0778bc39da5563" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "8a5c79d14bf2e91092b07f689f913ca8" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "1c95be408494c083af6b6f5257a42482" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "4f9fb868eaf1afa89f2b69ec3cee7cc3" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 30806016, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 24899584 + } + ], + "md5sum": "3d8f26ac117f2ac08bc1e991b5942f08" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "d980dcc69c314e29f2ec66d3be3a8bb1" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "a147f7d8385261420852f17ca138c749" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "507340d5a6d2db924ae14dfd04788f90" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "dd614ed6a5f48715cd5506174e1726a6" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "f350114b7f70a1cb1c9f2dd0caeba2cf" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "b7a6f10c0487c6c8560f4ded0b7afb92" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "d55157860429377ce24de10bdd70bee4" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "b221c567c074878d3ee523d393a291a4" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "06edca396573daafeb95815cfaf599cf" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "1c9743cc0f1e9d8d74d5a26b01302cde" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "e16ac2e27aa50af70ee6a53afc0097bb" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "385666d74912eb95af61c1c054c29558" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "bf56654bf18132289641296f97ae7269" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "a4b8a22c9558a6ad82a63f979be15301" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "26e64bd40c9f958ae2686bb672475274" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "4c254ad5cca965ca5f7f214a2644167b" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "13024924e7c9b484231c276f495c82d1" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "786e7571650baed4f9cbc8ef0d3d0e4a" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "36b35cd8969112d70bfbb554bc773a54" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "016665062c18f236bfe0cf5f3a5dc978" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "a872e981e4260a3d54fa3248405e18e3" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "c81d8e4a1e9c4714aad0208853b01cca" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "75974696b5ef05c2b1e1b58d6981d233" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "b7a9684af02f0d68af209a717a0abcd4" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "404db2114bb0d0e6de96c29246731556" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "57959dea194b90ea371508511686b24e" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 18984960 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 18993152 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 21934080 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 27840512 + } + ], + "md5sum": "9996710b4220dbe99421af5bff2d45a7" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 30375936, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 0 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 10125312 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 11390976 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 18141184 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 18984960 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 29110272 + } + ], + "md5sum": "62f5b1537157139c20ab3b0376570bf9" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 31129600, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 0 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 6750208 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 7593984 + }, + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 7602176 + } + ], + "md5sum": "625a0d286141f96d5b783736fef404f8" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "5741af27e6121685f9598c2ada3919ff" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 29425664, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 0 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 2940928 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 2949120 + }, + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 2957312 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 26484736 + } + ], + "md5sum": "c27ac8a521baeab9c8ea4313e3c89f35" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "1c9bacabb5e101e6b3652e4eb9130744" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "66a9b045139720c07dc0c9bc3a50dffe" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "a305cce1a99959810935b0873aeacff1" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "3376beba16201102ff9716ae954f30c4" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 32391168, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5914624 + }, + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 5922816 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 29450240 + } + ], + "md5sum": "e6392e32905b8a4a35de4fb300915796" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "f6d054df1edb4862106601b699a62edb" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "c89a62c4af6642df1b484416fa2beab0" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "eb02860d33fae40e2bc608d4ec1144e2" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "3c0140383dadb39f2b448f14f3d3567a" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "6ee336316d5b5f1ca382efabec8e18fa" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "8aa69bcea4bd96626517e8d47c4c645f" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "152dd60a22d561449cfddcf7dc692bd7" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "03a31855edcf687d06301d9015f1f1a6" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "d428ffc029259f6e5ea13ac3fe93f263" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "a58bdb1694534268ce9d70336f2f11ec" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "af9e9ede2dbf014d688daa99e2ccec28" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "5ffd43db0313bef30d0bd92750021bf8" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "246a79c13fde5abdcbe3b3ab45556fcf" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "791ffbc60335d45faf7ca829f1c84a72" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "c664c0eab4da8be97528567965774ee8" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "2a74218b6ff7c621fc62b3ce875cdc80" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "754815325f9b772cbb663ca02aed3cb3" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "0fa76a72d925d3d37a02e6a55f222528" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "58cdef7bd0bde635260bd2793de00a44" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "a120c41e2f8afd30a55ca3d85b412f9c" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "1abad8650a6579c52156f9f577d4d6b5" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "27615f23f60962720845d011ad42ac21" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "e766a9339419587a28f943e7cc1b874a" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "6e04be1d19855c058ca0f78d5de832f4" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 23527424, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 4096, + 1436 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 23527424, + "byteOffset": 0 + } + ], + "md5sum": "66903566f3671a833f644af575acb899" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 47251456, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 28672, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 47251456, + "byteOffset": 0 + } + ], + "md5sum": "cfb5fc4d05bc12d507b5347efc36f2f6" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 27848704, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 24899584 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 4096, + 359 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 2940928, + "byteOffset": 24907776 + } + ], + "md5sum": "0208283ace834e5f369597e89e5dd4fa" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 24899584, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 28672, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5906432, + "byteOffset": 0 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 4096 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 8192, + "byteOffset": 5906432 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 6144, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 10125312, + "byteOffset": 5914624 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 6144, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1265664, + "byteOffset": 16039936 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 4096, + 412 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 6750208, + "byteOffset": 17305600 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 4096, + 103 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 843776, + "byteOffset": 24055808 + } + ], + "md5sum": "0185ba75257dfd8346b4c6a7d0a240bf" + } + ] +} \ No newline at end of file