| { |
| "metadata": { |
| "ParamSize": 325, |
| "ParamBytes": 4073866240.0, |
| "BitsPerParam": 4.500422792921966 |
| }, |
| "records": [ |
| { |
| "dataPath": "params_shard_0.bin", |
| "format": "raw-shard", |
| "nbytes": 65540096, |
| "records": [ |
| { |
| "name": "lm_head.q_weight", |
| "shape": [ |
| 32002, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 65540096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1e0c6925f95a3dfddae73ab55ae62043" |
| }, |
| { |
| "dataPath": "params_shard_1.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b33cb539b7c1399127d83e042ac62b8c" |
| }, |
| { |
| "dataPath": "params_shard_2.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "801df0d5fbbfbd8044d196abfde45770" |
| }, |
| { |
| "dataPath": "params_shard_3.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.23.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "407c94c8ddd0d61db431cc63dcc501eb" |
| }, |
| { |
| "dataPath": "params_shard_4.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "36197d1a35070c1d092e6df404865c0d" |
| }, |
| { |
| "dataPath": "params_shard_5.bin", |
| "format": "raw-shard", |
| "nbytes": 30245376, |
| "records": [ |
| { |
| "name": "lm_head.q_scale", |
| "shape": [ |
| 32002, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192512, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.22.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 8192512 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 8200704 |
| }, |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 11870720 |
| }, |
| { |
| "name": "model.layers.22.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 19210752 |
| }, |
| { |
| "name": "model.layers.23.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 19218944 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 19227136 |
| }, |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 22897152 |
| }, |
| { |
| "name": "model.layers.23.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30237184 |
| } |
| ], |
| "md5sum": "7f1b41cee63368776688fab772cef350" |
| }, |
| { |
| "dataPath": "params_shard_6.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3ded464286bbbca227f2988f73f23f29" |
| }, |
| { |
| "dataPath": "params_shard_7.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cf7f97a25f61de7bd1a7566681fd7920" |
| }, |
| { |
| "dataPath": "params_shard_8.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.23.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.23.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.23.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.24.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.24.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "3f82cc076011171c16ba2318e6c6b755" |
| }, |
| { |
| "dataPath": "params_shard_9.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.25.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "482df665477612c0167ab10c5cdf63f8" |
| }, |
| { |
| "dataPath": "params_shard_10.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.24.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.24.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.24.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.24.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.24.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.25.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "f067a3f79809068fe5805dce29fb4f93" |
| }, |
| { |
| "dataPath": "params_shard_11.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "05f1038c300686313efd3dd39ee52413" |
| }, |
| { |
| "dataPath": "params_shard_12.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.25.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.25.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.25.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.25.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "bfa1a6d9159e9f1fccff236bcf23f5b6" |
| }, |
| { |
| "dataPath": "params_shard_13.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.26.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cff716549aa90fb2b6315c45a8f6868b" |
| }, |
| { |
| "dataPath": "params_shard_14.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "549e29f481444f67d37d58efcd77f2bc" |
| }, |
| { |
| "dataPath": "params_shard_15.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.25.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.25.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.26.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.26.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.26.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.26.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "0878831a8e9b9bba9bf2fcbc516073a4" |
| }, |
| { |
| "dataPath": "params_shard_16.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.27.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c50829f126bebb1d1ec75b1631a41d51" |
| }, |
| { |
| "dataPath": "params_shard_17.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "de24f8dd4b594e02c47e819a86ca81f4" |
| }, |
| { |
| "dataPath": "params_shard_18.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.26.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.26.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.26.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.27.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.27.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.27.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "a5fe3a36d184de9e844467196b41e7ef" |
| }, |
| { |
| "dataPath": "params_shard_19.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.28.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aa79256f614d8b9031746b3b8ef1bff0" |
| }, |
| { |
| "dataPath": "params_shard_20.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.28.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "67d084740e8afcf540c9b2bb77d09c24" |
| }, |
| { |
| "dataPath": "params_shard_21.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.27.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.27.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.27.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.27.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.28.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.28.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "4a1ef2018a3536f0770c2d2c4529efe9" |
| }, |
| { |
| "dataPath": "params_shard_22.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.29.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "994c47a45ad864ccc08994cfaa7f2e3b" |
| }, |
| { |
| "dataPath": "params_shard_23.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.28.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.28.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.28.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.28.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.28.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.28.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.29.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "b9436b98687dff6ce7a5b24fe1beb8a0" |
| }, |
| { |
| "dataPath": "params_shard_24.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.29.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d7e26306198271e03277b0616e0e766a" |
| }, |
| { |
| "dataPath": "params_shard_25.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.29.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.29.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.29.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.29.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.29.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "f55b235aa1817a4778a16120357b64fe" |
| }, |
| { |
| "dataPath": "params_shard_26.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.30.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9b40ee872d4b5fd80f85eec36ef811f8" |
| }, |
| { |
| "dataPath": "params_shard_27.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.30.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "1b97432bb0b9aac533cc031a1dc82655" |
| }, |
| { |
| "dataPath": "params_shard_28.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.29.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.29.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.30.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.30.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.30.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.30.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.30.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "7b2dffd83cfbbbde8aa3daae9f2ddd77" |
| }, |
| { |
| "dataPath": "params_shard_29.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.31.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "abf1bea97f3b105e320bc4c9b8f1b6ff" |
| }, |
| { |
| "dataPath": "params_shard_30.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.31.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "3868f9dfb6fd9a7668673a2757ada42a" |
| }, |
| { |
| "dataPath": "params_shard_31.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.30.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.30.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.30.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.31.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.31.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.31.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.31.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "1587031911f7df2bbeef31d1bd3dee58" |
| }, |
| { |
| "dataPath": "params_shard_32.bin", |
| "format": "raw-shard", |
| "nbytes": 65540096, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_weight", |
| "shape": [ |
| 32002, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 65540096, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f60cc46b6dc7d2cd7d7c2899aa2d4dfb" |
| }, |
| { |
| "dataPath": "params_shard_33.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "de5dfe4800c9ec2b0128bfcc29f15935" |
| }, |
| { |
| "dataPath": "params_shard_34.bin", |
| "format": "raw-shard", |
| "nbytes": 31801856, |
| "records": [ |
| { |
| "name": "model.layers.31.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.31.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.31.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.31.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.norm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.embed_tokens.q_scale", |
| "shape": [ |
| 32002, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192512, |
| "byteOffset": 23601152 |
| }, |
| { |
| "name": "model.layers.0.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 31793664 |
| } |
| ], |
| "md5sum": "96cb7c3f49626ad0929d188565bdeada" |
| }, |
| { |
| "dataPath": "params_shard_35.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "982ce832d4d1315a85c0a39b921b7831" |
| }, |
| { |
| "dataPath": "params_shard_36.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.0.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.0.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.0.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.0.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "26ccad496e625823103405c11899ad49" |
| }, |
| { |
| "dataPath": "params_shard_37.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7da7d7d6d5e774153f420a3af843d4d3" |
| }, |
| { |
| "dataPath": "params_shard_38.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "65e47809ccbfecbd92babe300a47b10d" |
| }, |
| { |
| "dataPath": "params_shard_39.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.0.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.1.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.1.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.1.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.1.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "99cb9bb2821edd506367c1d094f49637" |
| }, |
| { |
| "dataPath": "params_shard_40.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "07fb99328eaaa4cd7c8028f65816c525" |
| }, |
| { |
| "dataPath": "params_shard_41.bin", |
| "format": "raw-shard", |
| "nbytes": 32505856, |
| "records": [ |
| { |
| "name": "model.layers.1.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.1.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 18350080 |
| }, |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 30932992 |
| } |
| ], |
| "md5sum": "6a84a419ad7261f7b83c6e45c68920a5" |
| }, |
| { |
| "dataPath": "params_shard_42.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "10308add104a929db9e6cf304d8b86b9" |
| }, |
| { |
| "dataPath": "params_shard_43.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "c14ac6b938667e88bb2a40dd52279405" |
| }, |
| { |
| "dataPath": "params_shard_44.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.2.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.2.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "746aab5cbb88531dfda44d88c08bbdeb" |
| }, |
| { |
| "dataPath": "params_shard_45.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "7b8503cb0b0be70768f6bb03388d0886" |
| }, |
| { |
| "dataPath": "params_shard_46.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "5672de090ccfa6c3df6297cc673245a8" |
| }, |
| { |
| "dataPath": "params_shard_47.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.3.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.3.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "f724dd98bf6a20a42a3fcf20e76b5c07" |
| }, |
| { |
| "dataPath": "params_shard_48.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "060a0cc108db3b89843018322c1a934f" |
| }, |
| { |
| "dataPath": "params_shard_49.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "03f43f63daa3fe8190f44b2d5b489e53" |
| }, |
| { |
| "dataPath": "params_shard_50.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.4.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.4.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "6edb76703daf5ae9fd6ace5e81634a25" |
| }, |
| { |
| "dataPath": "params_shard_51.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "596214c551223e16fd79621797ab9a92" |
| }, |
| { |
| "dataPath": "params_shard_52.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.5.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "c7d338fd0d54749bb288c0ac4a41a5e4" |
| }, |
| { |
| "dataPath": "params_shard_53.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "55510aa393f4ba46c5f59c44ed732473" |
| }, |
| { |
| "dataPath": "params_shard_54.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.5.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.5.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "043377d4b450176ab4b23dd774dbab31" |
| }, |
| { |
| "dataPath": "params_shard_55.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.6.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ba4baf4044e23c8d46e9ad4699dd87c9" |
| }, |
| { |
| "dataPath": "params_shard_56.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "cd51ac12f8651ad69e5f4110c4fc19ab" |
| }, |
| { |
| "dataPath": "params_shard_57.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.6.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.6.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "7cad40adfc078d82dacaa3b1c0954169" |
| }, |
| { |
| "dataPath": "params_shard_58.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "a67e41ab3400e4a084b88ffd5fd026bd" |
| }, |
| { |
| "dataPath": "params_shard_59.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "2433a8a69f25319f024f5718eb773246" |
| }, |
| { |
| "dataPath": "params_shard_60.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.7.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.7.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "ac07435e1661ac0093283ac7b1ac7b59" |
| }, |
| { |
| "dataPath": "params_shard_61.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "75eb8b8c4e2f8036fae55f6efe404d6c" |
| }, |
| { |
| "dataPath": "params_shard_62.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ee75edeed8a3b2aa76dd7c3fb8f0010c" |
| }, |
| { |
| "dataPath": "params_shard_63.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.8.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.8.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "a847d9d88ff12855e222e6265c8467b0" |
| }, |
| { |
| "dataPath": "params_shard_64.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "defed3c9fb81324c776250bc5d83a796" |
| }, |
| { |
| "dataPath": "params_shard_65.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.8.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.9.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "9fb9b7b2caa527183fa8fdb2f4c39fb8" |
| }, |
| { |
| "dataPath": "params_shard_66.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "d40561f9914115e7b211a065d2089897" |
| }, |
| { |
| "dataPath": "params_shard_67.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.9.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "47cf5ef4b93364bddc1b506c6cce8fab" |
| }, |
| { |
| "dataPath": "params_shard_68.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.10.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "80d14057c307739cd52471f9034c6d98" |
| }, |
| { |
| "dataPath": "params_shard_69.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "105cf92ca886842f1d89b7fe61c90b44" |
| }, |
| { |
| "dataPath": "params_shard_70.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "9018a6f2ba62c81b300d4234e020f77e" |
| }, |
| { |
| "dataPath": "params_shard_71.bin", |
| "format": "raw-shard", |
| "nbytes": 24150016, |
| "records": [ |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.10.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.10.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.10.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.11.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 13123584 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 13131776 |
| }, |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 16801792 |
| }, |
| { |
| "name": "model.layers.11.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 24141824 |
| } |
| ], |
| "md5sum": "78761cd1983da59e745c69f95a4a7771" |
| }, |
| { |
| "dataPath": "params_shard_72.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f90958eb5626e0365c521079061866cd" |
| }, |
| { |
| "dataPath": "params_shard_73.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "30c5061b719909980c00a2c3b783ed7d" |
| }, |
| { |
| "dataPath": "params_shard_74.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.11.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.11.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.11.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.12.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.12.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "18e53a4f2f76bec99be7534b94d513e1" |
| }, |
| { |
| "dataPath": "params_shard_75.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "aaf2471d98cb03e3eca7fb30c04e9e34" |
| }, |
| { |
| "dataPath": "params_shard_76.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.12.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.12.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.12.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.12.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.13.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "b539ee244b63cd83ab12a028a293a40c" |
| }, |
| { |
| "dataPath": "params_shard_77.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "03c17ac29a27f5ea96d966d58d0b60f1" |
| }, |
| { |
| "dataPath": "params_shard_78.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.13.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.13.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.13.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.13.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "c62dc3d825ac73bb432f6d4575e01f2a" |
| }, |
| { |
| "dataPath": "params_shard_79.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.14.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "91abefb1635ed038fa56ee8b9306d3a4" |
| }, |
| { |
| "dataPath": "params_shard_80.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e70d0f00c5b669901ba8fc097b769752" |
| }, |
| { |
| "dataPath": "params_shard_81.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.13.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.14.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.14.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.14.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.14.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "602e2b58caa5b4129245c253638b3ece" |
| }, |
| { |
| "dataPath": "params_shard_82.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "6b60f7cf6007fdd72e15f8a2726c695e" |
| }, |
| { |
| "dataPath": "params_shard_83.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "51402205103d7481e4fcb26d24fd5a58" |
| }, |
| { |
| "dataPath": "params_shard_84.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.14.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.14.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.15.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.15.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.15.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "299f18388ac8d7e3cb2107653f6796c5" |
| }, |
| { |
| "dataPath": "params_shard_85.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f35da420fd74d1fb3676fdd033940171" |
| }, |
| { |
| "dataPath": "params_shard_86.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ee53b3657aaa2b07ef4f6a6886ff93c9" |
| }, |
| { |
| "dataPath": "params_shard_87.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.15.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.15.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.15.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.16.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.16.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "534b117b841496b2d8a46bbee5f8af6d" |
| }, |
| { |
| "dataPath": "params_shard_88.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "e4d2dd62ec39ae2d80d51d23ecefbddc" |
| }, |
| { |
| "dataPath": "params_shard_89.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.16.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.16.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.16.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.16.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.17.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "668a3bdb84acdd115e0c608c0e5d52d1" |
| }, |
| { |
| "dataPath": "params_shard_90.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f2076c1e77b21d4025c733a8c42f1593" |
| }, |
| { |
| "dataPath": "params_shard_91.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.17.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.17.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.17.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.17.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "4bc04e930a18cc77187bb3703d856c9a" |
| }, |
| { |
| "dataPath": "params_shard_92.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "4dce688d654c2c4bd968ee52cdf25f5c" |
| }, |
| { |
| "dataPath": "params_shard_93.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f56060d0949c1e62ffa9881f53862215" |
| }, |
| { |
| "dataPath": "params_shard_94.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.17.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.18.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.18.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.18.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.18.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "fbb991e8ce284d297efa71a85cd28074" |
| }, |
| { |
| "dataPath": "params_shard_95.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "8655bc81919a493b274aa9f67f8a8947" |
| }, |
| { |
| "dataPath": "params_shard_96.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b24bfb6928092fed3ea6b5901227fc2e" |
| }, |
| { |
| "dataPath": "params_shard_97.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.18.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.18.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.19.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.19.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.19.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "143fa6113ba71f58056578454e61383f" |
| }, |
| { |
| "dataPath": "params_shard_98.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b11a58117ebe8b6eacb39c5c3c31a79f" |
| }, |
| { |
| "dataPath": "params_shard_99.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "b92ddc716621ab94d82e04aad34fa582" |
| }, |
| { |
| "dataPath": "params_shard_100.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.19.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.19.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.19.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.20.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.20.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "e8923cc36b5a774550b5f00274bf6aa8" |
| }, |
| { |
| "dataPath": "params_shard_101.bin", |
| "format": "raw-shard", |
| "nbytes": 29360128, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "64d4ae987453d7e06793c379bb51269e" |
| }, |
| { |
| "dataPath": "params_shard_102.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.20.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.21.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "f98470039110dae287256d7ed1959333" |
| }, |
| { |
| "dataPath": "params_shard_103.bin", |
| "format": "raw-shard", |
| "nbytes": 58720256, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", |
| "shape": [ |
| 28672, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 58720256, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "76c5640b638b0719d58e3d4942c404a5" |
| }, |
| { |
| "dataPath": "params_shard_104.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.21.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.21.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.21.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.21.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "31e9e21a809dde2b4c99f800f0aa9bf5" |
| }, |
| { |
| "dataPath": "params_shard_105.bin", |
| "format": "raw-shard", |
| "nbytes": 33030144, |
| "records": [ |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.21.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 22020096 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 31981568 |
| } |
| ], |
| "md5sum": "229bb58603408d164350a08edc054fec" |
| } |
| ] |
| } |
