{ "metadata": { "ParamSize": 318, "ParamBytes": 925540352.0, "BitsPerParam": 4.502434662621765 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 102760448, "records": [ { "name": "lm_head.q_weight", "shape": [ 256, 100352 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 102760448, "byteOffset": 0 } ], "md5sum": "cd0989aa56821815bb821d196c65fd22" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 102760448, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 100352, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 102760448, "byteOffset": 0 } ], "md5sum": "36c1b473440a061117bfcf5d9a8e539b" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 32186368, "records": [ { "name": "lm_head.q_scale", "shape": [ 64, 100352 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12845056, "byteOffset": 0 }, { "name": "model.embed_tokens.q_scale", "shape": [ 100352, 64 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12845056, "byteOffset": 12845056 }, { "name": "model.layers.0.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25690112 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 25694208 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 25698304 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 31465472 } ], "md5sum": "88f0912e918eeb96c5e80ea13bb5b865" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.0.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.0.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.1.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "f3cf1f5b11d42204bc175174b8f96077" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.1.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.1.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.10.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "bf38ed6e2567dabd9762d74405b20dae" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.10.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.10.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.11.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "1d1cd43f1761a321fab29cda1999007e" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.11.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.11.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.12.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "62e2627928d78aad5c15fffeebfdcd45" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.12.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.12.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.13.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "57d49dc40e92f39a9a5858f2734b8efc" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.13.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.13.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.14.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "f8863c59f8763b32a2389558ab4ca208" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.14.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.14.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.15.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "309cc31b2987319f7e5db16c53a34148" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.15.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.15.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.16.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "1bae27daf9de54644ddeeb733c115260" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.16.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.16.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.17.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "964facdd5e767006232e8a9701b5d8a2" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.17.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.17.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.18.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "cabd88aeb67edfb671cf0c4c9136882d" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.18.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.18.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.19.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "0689b33b08e0885a92144ee1b3b2f334" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.19.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.19.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.2.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "ac802f46ace9b3bd313a7412eb261b12" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.2.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.2.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.20.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "0141fb5394b0b25e4bb44c485f9ef076" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.20.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.20.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.21.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "6ce983251a060b025946f30a5d17eef0" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.21.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.21.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.22.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "4e4c4286ac2eb11746b81cdaa3bb3e28" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.22.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.22.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.23.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "56137af00b213c97d6fb96738d586489" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.23.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.23.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.3.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "69e495f9bac3ac6fb9d6f5032590f156" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.3.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.3.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.4.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "4822052f347e99758424523a9e12ced1" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.4.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.4.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.5.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "e8e9da609fcfe74a6969fc4c6169aa3b" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.5.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.5.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.6.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "867f0b45cc82568291f28907c613c386" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.6.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.6.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.7.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "9c6cfab521fdaa54df1b84fc18e8952e" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.7.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.7.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.8.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "73dee516c955683d8ef124b0d1236e82" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 28930048, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.8.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.8.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.layers.9.input_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 704, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 5767168, "byteOffset": 22441984 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 176, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 720896, "byteOffset": 28209152 } ], "md5sum": "968a9b4f4f6c8f9cea4ce8ed28af55be" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 22441984, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 256, 11264 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 11534336, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 64, 11264 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1441792, "byteOffset": 11534336 }, { "name": "model.layers.9.post_attention_layernorm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12976128 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 12980224 }, { "name": "model.layers.9.self_attn.qkv_proj.bias", "shape": [ 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 12288, "byteOffset": 12984320 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 256, 6144 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 12996608 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 64, 6144 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 786432, "byteOffset": 19288064 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 256, 2048 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 20074496 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 64, 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 262144, "byteOffset": 22171648 }, { "name": "model.norm.bias", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22433792 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4096, "byteOffset": 22437888 } ], "md5sum": "f66fad58e5eae4c889f1ddfc4cf940e3" } ] }