{ "metadata": { "ParamSize": 243, "ParamBytes": 1069948928.0, "BitsPerParam": 5.001583230915965 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 49152, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "2bc830b32bf4a3e2443cd7c7d7eb3049" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 32509952, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 49152, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 6291456 }, { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 6295552 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 14684160 }, { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 15732736 } ], "md5sum": "321ce2e3370ed5cad59d72f84ceab5de" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "248185ae8708c8b9796f25d6a723a411" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 32522240, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 2097152 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 2101248 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 8392704 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 9179136 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 11276288 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 11538432 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11542528 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 19931136 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 20979712 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 23076864 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 23080960 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 29372416 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 30158848 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 32256000 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 32518144 } ], "md5sum": "55dc5539eebd937971046278a26281cb" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "0e1169af77fc87f2cbc2cd735641a5cd" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "36c12b0dd6800373f8f19eea41894846" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "0d43f39b7b4b86a9383e8645315e3b41" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "c42dc2ab82e92902027114336cf929a6" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "20affcf3c4b526bc50ce7510636e2d92" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "b58e9f1d97d38083f6bad2ce0cbc48e4" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "8ce527836a76f0bcc7bab92ca9a4dc6d" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "4c47c8b51b4c6ff74810682d2509e25f" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "cd4de2d5ed769f6c6df5f9950ded682f" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "d04d89f6c9d03f2ec954d0985d76b9c4" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "a911108f6b4bafde4355979dcfe9139d" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "bc2f0f9f26563eb40a006e373cd455a9" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "b4f7ba4fde8db8a464cda95c7dc676fa" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "6149f99b064340a00cac64393a04714d" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "6fd4dd6ff44e0937748da98434a34ee3" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "6066ce037be3e3b8e69bf6adfa6d5540" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "0b1738132eeaa83e69764d2efcebd45a" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "03012c9f5cd1062b40b434f661cc9558" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "7a717b92d0f5bf9bb8ad490c8db16850" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "e95f90505738f547264e91d96e40e504" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "72bdfadaaba3b78942c2884c9cf90d53" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "02b8945c4b906c24be436293accdcb56" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "3aae4c0990a06e8911483134d34933cf" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "152d30299a6ccf28bb5c7f16f9bb3fd9" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "881bf464381365a6a2e3186fbbcfc4cb" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "7cd735450677a1eddb5ae17fd98b77ad" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "2672651a55ea20361cdf03078cf3da79" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "5f6b618b8b314b9b2b30f77b09899a9a" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "beb9379c0f3ea83fe87cb6d87f91e122" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "762efc03cbe1e86e31c73674133046b5" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28315648, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 9437184 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 26214400 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 28311552 } ], "md5sum": "d21bec42278d9cfcc1e65960774ae98f" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 16384, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "243beb89b9d1b9e9073adf728f43f728" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 30420992, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 6291456 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 7077888 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 9175040 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 9437184 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 2048, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 9441280 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 2048, 256 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 17829888 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 16384, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2097152, "byteOffset": 18878464 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 20975616 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6291456, "byteOffset": 20979712 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 786432, "byteOffset": 27271168 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 2048, 256 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 2097152, "byteOffset": 28057600 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 2048, 64 ], "dtype": "bfloat16", "format": "raw", "nbytes": 262144, "byteOffset": 30154752 }, { "name": "model.norm.weight", "shape": [ 2048 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4096, "byteOffset": 30416896 } ], "md5sum": "9c0531b21d70fb1ce7243d000f5fc95c" } ] }