| { |
| "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": "86766bef9eb61e940c85fba490d9f9ed" |
| }, |
| { |
| "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": "fa105bee4aa32f8bf4f342ee8385296f" |
| }, |
| { |
| "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": "b273fa59cdfdd1f4d5487378775cb170" |
| }, |
| { |
| "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": "7a50e3dd8d2eea8ea391d49d056ed142" |
| }, |
| { |
| "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": "a996e623c933a3ce03b32876f55e40f9" |
| }, |
| { |
| "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": "5993083478f4a8c811ef3175683eb358" |
| }, |
| { |
| "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": "c58dcf0d4aae946670183c27e45f0c6e" |
| }, |
| { |
| "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": "588e1e2755935dacc0b07591e5ec6a55" |
| }, |
| { |
| "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": "86d9a640e4b2eee8edf08af20f901708" |
| }, |
| { |
| "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": "ed6a4f441985c396eb771f5844c21095" |
| }, |
| { |
| "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": "74a02920b4d5aa252fa1d7ba4ed91711" |
| }, |
| { |
| "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": "7da7894175287d0acdec1e106787eb9c" |
| }, |
| { |
| "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": "289457611bf079fc2902747ede90fd4d" |
| }, |
| { |
| "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": "80301f7bdd8a10ad5efeed89cfe6b3c7" |
| }, |
| { |
| "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": "6785eb4cd3d0766fb41bfc8510ec2df6" |
| }, |
| { |
| "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": "344788291f91b3e3c99d204215038283" |
| }, |
| { |
| "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": "65beb7d26c12c64a6ff7c91f64550c42" |
| }, |
| { |
| "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": "a4dbfa485ca6b1264dab350fe766f1e9" |
| }, |
| { |
| "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": "618dea8a5c4e88b579a130af2d6e1f63" |
| }, |
| { |
| "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": "9d1b21930c8fc5e8816f71de53a66f34" |
| }, |
| { |
| "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": "4a54e084a48498096c70e42309ce974b" |
| }, |
| { |
| "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": "fbdb6ab4e32a01b5df8fdae5e8c74c1f" |
| }, |
| { |
| "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": "a8674c0c962847e998068f26d611f81c" |
| }, |
| { |
| "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": "b93220db4f89d21cb96ca65dc148d059" |
| }, |
| { |
| "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": "b9e3887363364c79ace4b03a72b4565c" |
| }, |
| { |
| "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": "3b203d54a69e5c358ca9bd3c0fca77e5" |
| }, |
| { |
| "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": "5aa31975f444b9073f83cc7358b71cb4" |
| }, |
| { |
| "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": "a626df72a893ff2ad53d32b59d18f883" |
| }, |
| { |
| "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": "17054d2f038f1ca479f08d04e36f1b17" |
| }, |
| { |
| "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": "ce0236c0e0925cafc8f66fc2c29de6cd" |
| }, |
| { |
| "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": "64d4fa444eeda2cc734933ca8df43aab" |
| }, |
| { |
| "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": "8fb00ac94d66af1f1e05da35fdbffed6" |
| }, |
| { |
| "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": "223b1cd8ddd4f68033f8a7ed086c1eb8" |
| }, |
| { |
| "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": "9c461a252cf61a40e89a4417206a4b0a" |
| }, |
| { |
| "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": "b42bc6141ab91ab493931726ac073da4" |
| }, |
| { |
| "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": "76dc518918dd7922537fd480e3142b99" |
| }, |
| { |
| "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": "84263ab33f35d974f6e757512d673f28" |
| }, |
| { |
| "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": "8d6122cf09e05930477d5260eb63908e" |
| }, |
| { |
| "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": "c221047cab10f9d050f14c7622adbdb6" |
| }, |
| { |
| "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": "ea7716e89b3d3dd5096e610af6628e35" |
| }, |
| { |
| "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": "70eb69edbf1ccabe977fd54340335d72" |
| }, |
| { |
| "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": "f0edacf80fcc1cbe40f9910771477313" |
| }, |
| { |
| "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": "b4580940bf674e57d176a3693fc11703" |
| }, |
| { |
| "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": "b620bec8ca6d88b49670351dd014c80c" |
| }, |
| { |
| "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": "c06015afb00be4a9fa02d8284ca741c0" |
| }, |
| { |
| "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": "d0cfefc1f540bf34d34ddb660988cd84" |
| }, |
| { |
| "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": "022ff3c23d350e6ebfa0a47a92eebf00" |
| }, |
| { |
| "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": "59661bfd960ae527c3716caa66b109bb" |
| }, |
| { |
| "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": "90ce54e77f53b5cae4343cf28fb85ea9" |
| }, |
| { |
| "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": "4bef3c04f20f598e247e4ca8158c9404" |
| }, |
| { |
| "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": "365bfef276c3813723ddfb46500c5f27" |
| }, |
| { |
| "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": "b8874e2eaeccebc0f71d771b6eaa701a" |
| }, |
| { |
| "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": "c90d1543fca68d4734bcc741bacb6436" |
| }, |
| { |
| "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": "65c1b658ea0af1dd041b43362c035f93" |
| }, |
| { |
| "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": "9bd508fedce5e9c6e0b1734435a060ce" |
| }, |
| { |
| "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": "acf4fddceb8dad0c6b6a76bc008c8c9a" |
| }, |
| { |
| "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": "18d9d8caf80d99295934757ce7b02a5c" |
| }, |
| { |
| "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": "9c3d07a9b22f2f97225cff8c8982c2d4" |
| }, |
| { |
| "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": "7f3d721aa7832728f25d156a700fc521" |
| }, |
| { |
| "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": "298380d6358b9f2caeeb68355fb6afe3" |
| }, |
| { |
| "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": "5e9c7258a61ee2498e910515541116be" |
| }, |
| { |
| "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": "5eca21204e8988503a46d1cfd2de3bcf" |
| }, |
| { |
| "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": "aafe709bb6d0c12491c3d5be8ff69e09" |
| }, |
| { |
| "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": "84a6882f14b2a84e302e2207c626b8fd" |
| }, |
| { |
| "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": "afd6128fc041498ba77f1744762ef1e3" |
| }, |
| { |
| "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": "af18f913dc01ad4ca650c9037cfdd9b0" |
| }, |
| { |
| "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": "59258bfc5511b6d9c6e4317d2152aa48" |
| }, |
| { |
| "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": "3bcf9626a0f20ad20008326a29881038" |
| }, |
| { |
| "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": "4ee979f328234f1c31f832ce1ccc4851" |
| }, |
| { |
| "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": "bc91d9d12ed86d234880802686849faf" |
| }, |
| { |
| "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": "6ed5170bc97d8af83d3fc7ab12f4b890" |
| }, |
| { |
| "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": "f177e308720af4495812fabf144e96d3" |
| }, |
| { |
| "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": "97ca5a29ed0615201172cf00cb041714" |
| }, |
| { |
| "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": "0065abc05ba94585acb7a3bdd20a8b31" |
| }, |
| { |
| "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": "e3e2e9b252f7e1f4817a076f9d3a2996" |
| }, |
| { |
| "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": "85da379ee79ea27e010d03efd4b64906" |
| }, |
| { |
| "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": "1fc7b000f0c48db629e0d0f77208f11c" |
| }, |
| { |
| "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": "fc9215b338af12ec86da975b50c155c9" |
| }, |
| { |
| "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": "be7a2617508262ed7afa1a7a0e9c78bc" |
| }, |
| { |
| "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": "34651e34f6d70768350e351b89b371b5" |
| }, |
| { |
| "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": "23b9c4f67e542f5a82950626990ff82f" |
| }, |
| { |
| "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": "bc189d78b24e408027b15ee6d0ba17a2" |
| }, |
| { |
| "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": "e2e8189c7844308753810e20a4c67747" |
| }, |
| { |
| "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": "40ef48c98e23924c1cdb94d6b0270fb4" |
| }, |
| { |
| "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": "e289195b0265d93d9dd54ce3471b80f0" |
| }, |
| { |
| "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": "55a046bdd348c1e771aed42908b3b149" |
| }, |
| { |
| "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": "937ac6da26b72523a0d9d23105d48bc3" |
| }, |
| { |
| "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": "8f50f1b8968c97531af754815625bc7b" |
| }, |
| { |
| "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": "33331832a2e04b194be7609a1f3753d5" |
| }, |
| { |
| "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": "f36b281ff2f72d8e82cfb40e401356a7" |
| }, |
| { |
| "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": "dd016302ec24af4e9502f5d4a706afc7" |
| }, |
| { |
| "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": "81d9f1feb2ffbf47a102ab2e2dc962a8" |
| }, |
| { |
| "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": "058a0491caf9671c6ba7f360b95d5d58" |
| }, |
| { |
| "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": "136e981686800a1136b379d502ca462d" |
| }, |
| { |
| "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": "7df66a3772282096ad08a26a0bd02a8a" |
| }, |
| { |
| "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": "2ed7adda2f9d51bcbf1055560440303b" |
| }, |
| { |
| "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": "960c5a00c096cef6d843d02c7725346a" |
| }, |
| { |
| "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": "e05b0bca4cfb03fc53744a93794d0482" |
| }, |
| { |
| "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": "9b961b0199540b50677e55ff53d58ebe" |
| }, |
| { |
| "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": "40e780cb076b2824ad3ead46059cea6c" |
| }, |
| { |
| "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": "443ee52ae81180ec5e915de8720f8468" |
| }, |
| { |
| "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": "3d3df474fc40c323900b33a19a33a387" |
| }, |
| { |
| "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": "22e46b0e7eca61a7766845e883cda453" |
| }, |
| { |
| "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": "1e0bdac2eb440c940c807c468cd65823" |
| }, |
| { |
| "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": "05b537c7c6b5932be8fbab70d4371936" |
| }, |
| { |
| "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": "4d7bdb0e370cd41b60472b8249a3d252" |
| } |
| ] |
| } |
