| { |
| "metadata": { |
| "ParamSize": 325, |
| "ParamBytes": 4517404672.0, |
| "BitsPerParam": 4.500381277757404 |
| }, |
| "records": [ |
| { |
| "dataPath": "params_shard_0.bin", |
| "format": "raw-shard", |
| "nbytes": 262668288, |
| "records": [ |
| { |
| "name": "lm_head.q_weight", |
| "shape": [ |
| 128256, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 262668288, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "f7e3d6ab4308393f9f1ba125bc14bff1" |
| }, |
| { |
| "dataPath": "params_shard_1.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": "7e103fcedef6f63a69060e00781a5de6" |
| }, |
| { |
| "dataPath": "params_shard_2.bin", |
| "format": "raw-shard", |
| "nbytes": 32841728, |
| "records": [ |
| { |
| "name": "lm_head.q_scale", |
| "shape": [ |
| 128256, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 32833536, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.31.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 32833536 |
| } |
| ], |
| "md5sum": "6470015cd53c83c830637091849d09e0" |
| }, |
| { |
| "dataPath": "params_shard_3.bin", |
| "format": "raw-shard", |
| "nbytes": 262668288, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_weight", |
| "shape": [ |
| 128256, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 262668288, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ba53bcbc5a7ad9bdf66a93b23571dfe2" |
| }, |
| { |
| "dataPath": "params_shard_4.bin", |
| "format": "raw-shard", |
| "nbytes": 32833536, |
| "records": [ |
| { |
| "name": "model.embed_tokens.q_scale", |
| "shape": [ |
| 128256, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 32833536, |
| "byteOffset": 0 |
| } |
| ], |
| "md5sum": "ec1f5c954a5962ff7a038ec0f8e110e2" |
| }, |
| { |
| "dataPath": "params_shard_5.bin", |
| "format": "raw-shard", |
| "nbytes": 33054720, |
| "records": [ |
| { |
| "name": "model.layers.31.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.31.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.norm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 3678208 |
| }, |
| { |
| "name": "model.layers.0.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 3686400 |
| }, |
| { |
| "name": "model.layers.0.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 3694592 |
| } |
| ], |
| "md5sum": "6cd1df67e730cc8822529b3ecfb9dd54" |
| }, |
| { |
| "dataPath": "params_shard_6.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": "e16bc126f18bac7ddde47f3e87446b96" |
| }, |
| { |
| "dataPath": "params_shard_7.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": "c45cf894b0e9e2ec63b972ed1a118d86" |
| }, |
| { |
| "dataPath": "params_shard_8.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": "18d3b39eeaae45b9cfca4cee27fbcfdf" |
| }, |
| { |
| "dataPath": "params_shard_9.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": "5d054817b80d5fd7900b51e5bc18daaa" |
| }, |
| { |
| "dataPath": "params_shard_10.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": "235d183f5ef0e57e33058d042cf90035" |
| }, |
| { |
| "dataPath": "params_shard_11.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": "74acd62652ae2602733eaa5947522ab7" |
| }, |
| { |
| "dataPath": "params_shard_12.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": "210863526c9cde9c70476461c87ff0ac" |
| }, |
| { |
| "dataPath": "params_shard_13.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "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.2.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.2.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.2.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "80db043e422eece9a466f99c7fe7ceb0" |
| }, |
| { |
| "dataPath": "params_shard_14.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": "7304bee4bd59e6bb0a111fba700a2064" |
| }, |
| { |
| "dataPath": "params_shard_15.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": "de1ef74a5cd411181c5806dd470927f0" |
| }, |
| { |
| "dataPath": "params_shard_16.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.2.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.2.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.3.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.3.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "ea0fd47d16f0677461fe624325df87ce" |
| }, |
| { |
| "dataPath": "params_shard_17.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": "24a9737c391334217893e8390c351d75" |
| }, |
| { |
| "dataPath": "params_shard_18.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.3.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.3.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.3.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.4.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "adfe4f3357197c22e68f3a0de932aaee" |
| }, |
| { |
| "dataPath": "params_shard_19.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": "eb2c5de44fc1bd9ea6e67e2070989fff" |
| }, |
| { |
| "dataPath": "params_shard_20.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.4.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.4.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.4.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "a95f180267f3933bb1c035fed457ad98" |
| }, |
| { |
| "dataPath": "params_shard_21.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": "bb1d415cbacce280ba5c58802c37c4c0" |
| }, |
| { |
| "dataPath": "params_shard_22.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": "cbdce75606c341ac475e7244022faf0d" |
| }, |
| { |
| "dataPath": "params_shard_23.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.4.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| }, |
| { |
| "name": "model.layers.5.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.5.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.5.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "cacfd1aec3d63696f943730e0ee81d40" |
| }, |
| { |
| "dataPath": "params_shard_24.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": "942f8b3e35dbbdc1fdce0f2fbc0fccea" |
| }, |
| { |
| "dataPath": "params_shard_25.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": "8529d22731701b7c4c27c51c838b433c" |
| }, |
| { |
| "dataPath": "params_shard_26.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.5.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.5.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.6.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.6.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.6.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "c636917fe9b3ac576ce7a79930bc2f11" |
| }, |
| { |
| "dataPath": "params_shard_27.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": "85a1f7a26edc62d5cc4dcc49eb7b5887" |
| }, |
| { |
| "dataPath": "params_shard_28.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": "e97a5f9b9589f6685144e6a3da6cd6c6" |
| }, |
| { |
| "dataPath": "params_shard_29.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.6.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.6.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.7.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.7.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "55cc3bd27342eba88ebf71431e0175bd" |
| }, |
| { |
| "dataPath": "params_shard_30.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": "4ead345e57e3fcb149719a8a0b1beda6" |
| }, |
| { |
| "dataPath": "params_shard_31.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.7.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.7.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.7.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.8.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "d1279f82229f63f3c0dd927f2ae820a9" |
| }, |
| { |
| "dataPath": "params_shard_32.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": "ae8f9817a84779c4af06783796f127d6" |
| }, |
| { |
| "dataPath": "params_shard_33.bin", |
| "format": "raw-shard", |
| "nbytes": 25174016, |
| "records": [ |
| { |
| "name": "model.layers.8.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.8.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.8.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "d5af7cb8247d545663640bc034605618" |
| }, |
| { |
| "dataPath": "params_shard_34.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": "d3e0414dcf92412dc85c6422b3c8f127" |
| }, |
| { |
| "dataPath": "params_shard_35.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": "2db3def54849e35dd2879749fc59dac8" |
| }, |
| { |
| "dataPath": "params_shard_36.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.8.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.8.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.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.10.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "238c00d82b4dbdc4a4e357b816c0ea23" |
| }, |
| { |
| "dataPath": "params_shard_37.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": "80cd699fa2c6feb6cd5bb623a00edd6a" |
| }, |
| { |
| "dataPath": "params_shard_38.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": "ff6793eb56cba37d676ba5234222a026" |
| }, |
| { |
| "dataPath": "params_shard_39.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.10.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.10.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.11.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.11.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.11.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "b2c8ada6b173cdcf107ab4c57f674f2e" |
| }, |
| { |
| "dataPath": "params_shard_40.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": "f18a4cab6cadecb1b6ede2f41bbc586c" |
| }, |
| { |
| "dataPath": "params_shard_41.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": "af2136c7e4ad892dc5ec0433d8c955cf" |
| }, |
| { |
| "dataPath": "params_shard_42.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": "0ae2aa7b582153a7cbb7ebf2170018e2" |
| }, |
| { |
| "dataPath": "params_shard_43.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": "cd0dac76753f10c04c353f17be4ee325" |
| }, |
| { |
| "dataPath": "params_shard_44.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": "4a73b08aeeb33a36a4c62184b6e65da8" |
| }, |
| { |
| "dataPath": "params_shard_45.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": "76081b8193631c1f51424187c11bfb4e" |
| }, |
| { |
| "dataPath": "params_shard_46.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": "7b358593d1f106577fc5c2a0f1ef6ed7" |
| }, |
| { |
| "dataPath": "params_shard_47.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": "f71f0736959eb118de70751f28d0b472" |
| }, |
| { |
| "dataPath": "params_shard_48.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": "7f900f8aa36250d3d90b7bbc08f443a4" |
| }, |
| { |
| "dataPath": "params_shard_49.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": "3dab961a342ab71def8fa0ad54bd7cbb" |
| }, |
| { |
| "dataPath": "params_shard_50.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": "74f1a7acb8d8cdf23181b18cdcfcd631" |
| }, |
| { |
| "dataPath": "params_shard_51.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": "a841f25c052be42d08234b5a242e6595" |
| }, |
| { |
| "dataPath": "params_shard_52.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": "4e81a69be6dfb3b5d2db7099d306cece" |
| }, |
| { |
| "dataPath": "params_shard_53.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": "dbbe00d79259ce75b45953b9556cd291" |
| }, |
| { |
| "dataPath": "params_shard_54.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": "f761ee93c977ca25ae18436575532bc7" |
| }, |
| { |
| "dataPath": "params_shard_55.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": "c4660188c74defdff2aed201c2860e6a" |
| }, |
| { |
| "dataPath": "params_shard_56.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": "1a2825d38cab7b2e88211673719dda07" |
| }, |
| { |
| "dataPath": "params_shard_57.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": "eba7106c05afabb3dec580e20b0b530d" |
| }, |
| { |
| "dataPath": "params_shard_58.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": "8ac505288241f9786160bf0d8e1e3924" |
| }, |
| { |
| "dataPath": "params_shard_59.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": "502d74ecc5dea5ae70fb6322e0184350" |
| }, |
| { |
| "dataPath": "params_shard_60.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": "283169178ed8b77333c95aa14361d805" |
| }, |
| { |
| "dataPath": "params_shard_61.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": "1d615682d4f466d8a02589c88c1eb04d" |
| }, |
| { |
| "dataPath": "params_shard_62.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": "e848c3a5b1bc176dcca2d68149b3595e" |
| }, |
| { |
| "dataPath": "params_shard_63.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": "069be50c5e93dc7f12874f13e35bc1e4" |
| }, |
| { |
| "dataPath": "params_shard_64.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": "fb275281a74f5cc7a0e01fde9a19d639" |
| }, |
| { |
| "dataPath": "params_shard_65.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": "6452b076184f73d64085a90f204c27ca" |
| }, |
| { |
| "dataPath": "params_shard_66.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": "2ab9a1553b1568902c50f6160ac15159" |
| }, |
| { |
| "dataPath": "params_shard_67.bin", |
| "format": "raw-shard", |
| "nbytes": 30932992, |
| "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.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 23592960 |
| } |
| ], |
| "md5sum": "b10b8f1eeb350a4c186f81b4334d059d" |
| }, |
| { |
| "dataPath": "params_shard_68.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": "7192f93372c505264db6f34037881131" |
| }, |
| { |
| "dataPath": "params_shard_69.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": "68bae98f5b1087fe35e1d22b4d818ed1" |
| }, |
| { |
| "dataPath": "params_shard_70.bin", |
| "format": "raw-shard", |
| "nbytes": 27271168, |
| "records": [ |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.20.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 12582912 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 14155776 |
| }, |
| { |
| "name": "model.layers.20.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 22544384 |
| }, |
| { |
| "name": "model.layers.9.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 23592960 |
| }, |
| { |
| "name": "model.layers.9.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 23601152 |
| } |
| ], |
| "md5sum": "2bc6ba1bf0b7a9efba8a5ef94b73a031" |
| }, |
| { |
| "dataPath": "params_shard_71.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": "a91fa5ac7da2f15d0bcc7672e0371ccf" |
| }, |
| { |
| "dataPath": "params_shard_72.bin", |
| "format": "raw-shard", |
| "nbytes": 30949376, |
| "records": [ |
| { |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.9.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 7340032 |
| }, |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 7348224 |
| }, |
| { |
| "name": "model.layers.9.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 19931136 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 21504000 |
| }, |
| { |
| "name": "model.layers.9.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 29892608 |
| }, |
| { |
| "name": "model.layers.20.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 30941184 |
| } |
| ], |
| "md5sum": "a5a89844c51809f206a0f22001d0aee6" |
| }, |
| { |
| "dataPath": "params_shard_73.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "records": [ |
| { |
| "name": "model.layers.20.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.20.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 3670016 |
| }, |
| { |
| "name": "model.layers.21.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 3678208 |
| }, |
| { |
| "name": "model.layers.21.mlp.down_proj.q_weight", |
| "shape": [ |
| 4096, |
| 1792 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 29360128, |
| "byteOffset": 3686400 |
| } |
| ], |
| "md5sum": "df5beb7fac764fe0316d35cfefa7685d" |
| }, |
| { |
| "dataPath": "params_shard_74.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": "5a46d499c73379b10659996415540e2a" |
| }, |
| { |
| "dataPath": "params_shard_75.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": "4e0c319395be5cc86821e79d73b1604a" |
| }, |
| { |
| "dataPath": "params_shard_76.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": "b51b1bf2566e9df50830af613a2dec28" |
| }, |
| { |
| "dataPath": "params_shard_77.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": "9d8647b15d873bbebbc7f5328cba6c70" |
| }, |
| { |
| "dataPath": "params_shard_78.bin", |
| "format": "raw-shard", |
| "nbytes": 33046528, |
| "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.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 9437184 |
| }, |
| { |
| "name": "model.layers.22.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 9445376 |
| }, |
| { |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 13115392 |
| }, |
| { |
| "name": "model.layers.22.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 20455424 |
| }, |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 20463616 |
| } |
| ], |
| "md5sum": "63b57105dd0006521339a5a8c9f35c34" |
| }, |
| { |
| "dataPath": "params_shard_79.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": "1932ed4197a4c08c2a0bd4b552b3b981" |
| }, |
| { |
| "dataPath": "params_shard_80.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": "9876241b4b116bfacf6cafd5d7d3782e" |
| }, |
| { |
| "dataPath": "params_shard_81.bin", |
| "format": "raw-shard", |
| "nbytes": 22036480, |
| "records": [ |
| { |
| "name": "model.layers.22.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 1572864 |
| }, |
| { |
| "name": "model.layers.22.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 9961472 |
| }, |
| { |
| "name": "model.layers.23.input_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.23.mlp.down_proj.q_scale", |
| "shape": [ |
| 4096, |
| 448 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 3670016, |
| "byteOffset": 11018240 |
| }, |
| { |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 14688256 |
| }, |
| { |
| "name": "model.layers.23.post_attention_layernorm.weight", |
| "shape": [ |
| 4096 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 8192, |
| "byteOffset": 22028288 |
| } |
| ], |
| "md5sum": "66c4c10882bf326352c5f0bf1b764810" |
| }, |
| { |
| "dataPath": "params_shard_82.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": "35c5c4b68881c5ef4be58178761355c2" |
| }, |
| { |
| "dataPath": "params_shard_83.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": "a376c900ae2563f84c6fe67e3b2d1daa" |
| }, |
| { |
| "dataPath": "params_shard_84.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": "e87b60a428db4de3ceda4ff801999775" |
| }, |
| { |
| "dataPath": "params_shard_85.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": "10e5a8dec8862582fa4672c1ba87426c" |
| }, |
| { |
| "dataPath": "params_shard_86.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": "2d3a1b9e42f7a62d6f70cbc7463bc6a2" |
| }, |
| { |
| "dataPath": "params_shard_87.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": "c78aa9f89e646ce428add8d88e6ac2c4" |
| }, |
| { |
| "dataPath": "params_shard_88.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": "98913401844fe97a797c490eeeec458e" |
| }, |
| { |
| "dataPath": "params_shard_89.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": "d9ac76dc08f1ebb951393c8abc87b90c" |
| }, |
| { |
| "dataPath": "params_shard_90.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": "63b5fda4524e738d8d9cf2081e91f1a6" |
| }, |
| { |
| "dataPath": "params_shard_91.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": "b27425331a26004f35978c5782db9fe3" |
| }, |
| { |
| "dataPath": "params_shard_92.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": "2e9c8b88276b939710a76fae45df3a6b" |
| }, |
| { |
| "dataPath": "params_shard_93.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": "93764453e33cde6f70867a7ee9774b79" |
| }, |
| { |
| "dataPath": "params_shard_94.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": "cbf1983eef994b04eb70cc1eb8760692" |
| }, |
| { |
| "dataPath": "params_shard_95.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": "689e392bae6263bff0ee262d48ac830c" |
| }, |
| { |
| "dataPath": "params_shard_96.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": "a7683f27477cbf7ce0767951a332edde" |
| }, |
| { |
| "dataPath": "params_shard_97.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": "bac28140229263b8013044b3c0907b62" |
| }, |
| { |
| "dataPath": "params_shard_98.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": "75bd33bfecbc9272059d4f07984cb2d8" |
| }, |
| { |
| "dataPath": "params_shard_99.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": "79b65d64ab92e162fb1e16c3225db702" |
| }, |
| { |
| "dataPath": "params_shard_100.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": "e14ba6f5cdc0eb71cad2d75d80b68500" |
| }, |
| { |
| "dataPath": "params_shard_101.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": "b62849d578aa364fe30e19df0a278f93" |
| }, |
| { |
| "dataPath": "params_shard_102.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": "04cff11f2a593ce0a5b8739a0b9a2179" |
| }, |
| { |
| "dataPath": "params_shard_103.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": "e8d7327967682a84cc79519711d1109f" |
| }, |
| { |
| "dataPath": "params_shard_104.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": "da87cf701d04ecf864914b0f770a1b89" |
| }, |
| { |
| "dataPath": "params_shard_105.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": "f7421ae34c294223c1226696e9a0928e" |
| }, |
| { |
| "dataPath": "params_shard_106.bin", |
| "format": "raw-shard", |
| "nbytes": 32505856, |
| "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.mlp.gate_up_proj.q_scale", |
| "shape": [ |
| 28672, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 7340032, |
| "byteOffset": 11010048 |
| }, |
| { |
| "name": "model.layers.31.self_attn.qkv_proj.q_weight", |
| "shape": [ |
| 6144, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 12582912, |
| "byteOffset": 18350080 |
| }, |
| { |
| "name": "model.layers.31.self_attn.qkv_proj.q_scale", |
| "shape": [ |
| 6144, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1572864, |
| "byteOffset": 30932992 |
| } |
| ], |
| "md5sum": "0907ce03b266ee46af36ca557d6fd0ec" |
| }, |
| { |
| "dataPath": "params_shard_107.bin", |
| "format": "raw-shard", |
| "nbytes": 9437184, |
| "records": [ |
| { |
| "name": "model.layers.31.self_attn.o_proj.q_weight", |
| "shape": [ |
| 4096, |
| 512 |
| ], |
| "dtype": "uint32", |
| "format": "f32-to-bf16", |
| "nbytes": 8388608, |
| "byteOffset": 0 |
| }, |
| { |
| "name": "model.layers.31.self_attn.o_proj.q_scale", |
| "shape": [ |
| 4096, |
| 128 |
| ], |
| "dtype": "float16", |
| "format": "f32-to-bf16", |
| "nbytes": 1048576, |
| "byteOffset": 8388608 |
| } |
| ], |
| "md5sum": "de69d15347c465061baa6eab2ed5beeb" |
| } |
| ] |
| } |