| { | |
| "metadata": { | |
| "ParamSize": 325, | |
| "ParamBytes": 3631664128.0, | |
| "BitsPerParam": 3.617978559693305 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 211365888, | |
| "records": [ | |
| { | |
| "name": "lm_head.q_weight", | |
| "shape": [ | |
| 128256, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 211365888, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "568f86ab316027f797575a37c50a79d9" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "dd6e699104ec23157bd8ec691f540458" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 211365888, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_weight", | |
| "shape": [ | |
| 128256, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 211365888, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "23ee1db64fe9ec1de25677c5d5242b84" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 26420736, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_scale", | |
| "shape": [ | |
| 128256, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 26420736, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "da547dd4e70f656eb8f40d6d8956af59" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "95f762e8d76219a1872151a67b59c84a" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "269fe7bba2c54aa3480e4b58a115393d" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 32335360, | |
| "records": [ | |
| { | |
| "name": "lm_head.q_scale", | |
| "shape": [ | |
| 128256, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 26420736, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.31.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 26420736 | |
| }, | |
| { | |
| "name": "model.layers.31.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 26428928 | |
| }, | |
| { | |
| "name": "model.layers.31.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 29369856 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 29378048 | |
| }, | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 29386240 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 29394432 | |
| } | |
| ], | |
| "md5sum": "e1443c46e956116e908069a095305528" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e318db552ecb93bdee4c218c4db713e7" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "05a9bd34f29e9acf5a2219af15c8acd4" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "cb44fd7be0463f7bac4b17cfa63357ab" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eac88017bafff0769d72feb70376137b" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "aa41c90fd87d6828740135a8a69889ff" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "87f04b598c066f7109e5dd58a0eed6a0" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "69af82fc3117738ec1f865dd791bde2d" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c7b6fdaeb45cac104374a9f32c3530fe" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "3d04ed741e65a082ac9b5c10f0667e83" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "86e419f75c402d6b10762c64736781c5" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fde7af460d477e5243ad3dd5f99f9d91" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "868b5a7a096b0b94fc5d19415d0e8593" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5bcec89759604d5d2acff4e1d2a14c8d" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ff7596e9b3eb0ab4422b906aa8c6cde3" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "01ad9bb03fe3a97e1ff8b1d7b6624687" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fba5e7101395a7eab040c18d7aca3f3c" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d7d67bc05d6a646579e36f0c6d94f663" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "3b907fd0153bd507a5b3ba6cd8ab36e9" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "285b2c0e257a9e8f42113ba4a40f12cf" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "12c0dc94deaf06b2513c063b034d5f9b" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "9b0782e00a1a61c271227210b599b8f1" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cf7d04543b151a40f6f793c6c93465ba" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "60b7b2bab5344e7c77a1e31af8f2393c" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "81346474ce88da6d76c096931d8f9949" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2ce4bc27e1b9cb38f7ebda8b05054542" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fd339f4405ad0a058648b576c1ab8f80" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "ec3b1d226a915454ed10081aaae83ab6" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "de8c500964608e37d2bfa8db0a675c82" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e7321b16460914e7457f161bb8a579b4" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "b48256b2c742f78801dd751ea9144738" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eff6702b66a26500eb3ecb8fcee3b163" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "21b5e7a3ce245fc05bb7f3b4e5884f4c" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "8a0d16f0a79a3605cbac3cf4f589d111" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "24a6aeaafdf8f69c0f26109b51834d1f" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e9c668d4c5cc59a10c065cca669d6d2e" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "f1d7eebb10ada204ba146f5a35480947" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b49a6dd0e16e800418e9c9f69e90793c" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "42bb172e102276e94b230b62acc50d0a" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "77abf51dd5deee1610f473ffc226a6a0" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b92bd072e4b5878a3da868f46f775cd4" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4e52ad90c25e5c57c6f2fd5f20fdd51d" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "0d26838451054a31f15b5551acd7a494" | |
| }, | |
| { | |
| "dataPath": "params_shard_49.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d1ca00d725767e1ab6747f41f9470f34" | |
| }, | |
| { | |
| "dataPath": "params_shard_50.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "71a6116da9021978cff16fd984efdf5b" | |
| }, | |
| { | |
| "dataPath": "params_shard_51.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "e777d0ccd0bcbef35919835936721ea6" | |
| }, | |
| { | |
| "dataPath": "params_shard_52.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1b57969a33b7d2e2458738cd11911582" | |
| }, | |
| { | |
| "dataPath": "params_shard_53.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "36b10836d2280bcf78eb3041805ac478" | |
| }, | |
| { | |
| "dataPath": "params_shard_54.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "5c392300de5f3f673210d1348450e4a8" | |
| }, | |
| { | |
| "dataPath": "params_shard_55.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1160b750b48a8338c4cd396963898173" | |
| }, | |
| { | |
| "dataPath": "params_shard_56.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a3e4a3911e94b8af2b1dae018acc9d7c" | |
| }, | |
| { | |
| "dataPath": "params_shard_57.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "b3243ea7d57e01b11f6b3c0f66643c5a" | |
| }, | |
| { | |
| "dataPath": "params_shard_58.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d2bb347ef0a79d3d36a9d3e605e7fb06" | |
| }, | |
| { | |
| "dataPath": "params_shard_59.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4a6fab620da6e3a37236a034b1dcb381" | |
| }, | |
| { | |
| "dataPath": "params_shard_60.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 24899584 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 24907776 | |
| } | |
| ], | |
| "md5sum": "6214077974ba718e53ca534e49fe4431" | |
| }, | |
| { | |
| "dataPath": "params_shard_61.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1b59c0e5e3fbd07d12cf0bd16ec97e01" | |
| }, | |
| { | |
| "dataPath": "params_shard_62.bin", | |
| "format": "raw-shard", | |
| "nbytes": 30806016, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 5906432 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 5914624 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 16039936 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 17305600 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 24055808 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 24899584 | |
| } | |
| ], | |
| "md5sum": "61f34267118b05542abfcfa747d0b313" | |
| }, | |
| { | |
| "dataPath": "params_shard_63.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cb3648fcd4c4a12ec3f410bb7ad3b0b8" | |
| }, | |
| { | |
| "dataPath": "params_shard_64.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7f4173953f7a1c45963a3d5dd310445a" | |
| }, | |
| { | |
| "dataPath": "params_shard_65.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "5c6f385494acfaaa6c2b73dd5b93aac7" | |
| }, | |
| { | |
| "dataPath": "params_shard_66.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eb2fc14eb26353ce3bf13939427fd5a2" | |
| }, | |
| { | |
| "dataPath": "params_shard_67.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0ccca1ab4b7eb4fe1c5a239f0b8465fa" | |
| }, | |
| { | |
| "dataPath": "params_shard_68.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b85aff5b8468d32b5bcd05b186449b0a" | |
| }, | |
| { | |
| "dataPath": "params_shard_69.bin", | |
| "format": "raw-shard", | |
| "nbytes": 30806016, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 21942272 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 21950464 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 24891392 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 30797824 | |
| } | |
| ], | |
| "md5sum": "f73935ce12a04364fc6b6a4156bf14ea" | |
| }, | |
| { | |
| "dataPath": "params_shard_70.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5d388601195a6000960c8b7b02fff587" | |
| }, | |
| { | |
| "dataPath": "params_shard_71.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9d8709bd1f31406eacd05a099f41f490" | |
| }, | |
| { | |
| "dataPath": "params_shard_72.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "92ccc82c3aa13e345eddbf2ba095c644" | |
| }, | |
| { | |
| "dataPath": "params_shard_73.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a9e9a51cdba7ea8f9e5402ff557e17a8" | |
| }, | |
| { | |
| "dataPath": "params_shard_74.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fd6b3efdb24ff017a90666eeefba5448" | |
| }, | |
| { | |
| "dataPath": "params_shard_75.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "1bded92899e46174eda937f7a9be54fc" | |
| }, | |
| { | |
| "dataPath": "params_shard_76.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ff50142a8a7401f5785f3c268c80c6ef" | |
| }, | |
| { | |
| "dataPath": "params_shard_77.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "613fe8844c9cff179d43200fb10273cc" | |
| }, | |
| { | |
| "dataPath": "params_shard_78.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "8f8c11ad04b08958343cfe4fb15fc16f" | |
| }, | |
| { | |
| "dataPath": "params_shard_79.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "034f64229fd3d06435a6e6f7fcdf0919" | |
| }, | |
| { | |
| "dataPath": "params_shard_80.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bf20ebc5653ad5eddf4a9a42be8bfd78" | |
| }, | |
| { | |
| "dataPath": "params_shard_81.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "b886e3897147ee0e6ba2be22b4a99ebf" | |
| }, | |
| { | |
| "dataPath": "params_shard_82.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "28283fd33c9159683e384deb7a52a835" | |
| }, | |
| { | |
| "dataPath": "params_shard_83.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "497ac16a138ec3b5588a0d311e8b24f3" | |
| }, | |
| { | |
| "dataPath": "params_shard_84.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.26.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.26.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "17b0cb9e936a2b2e80cd419607ce262f" | |
| }, | |
| { | |
| "dataPath": "params_shard_85.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6505aee1559481b3f23adcde97d30259" | |
| }, | |
| { | |
| "dataPath": "params_shard_86.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ce12ecbf4f4c4364448c52e34793e44e" | |
| }, | |
| { | |
| "dataPath": "params_shard_87.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.27.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.27.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "3026ef09dc2cf50402a109fbd7162184" | |
| }, | |
| { | |
| "dataPath": "params_shard_88.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f5392b35cc8f220322a339f92b4e183d" | |
| }, | |
| { | |
| "dataPath": "params_shard_89.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7df894fe934b9189127a4ce093ab1611" | |
| }, | |
| { | |
| "dataPath": "params_shard_90.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.28.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.28.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.28.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.28.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "1b6c4a522936d2d821a14de0bbe298d2" | |
| }, | |
| { | |
| "dataPath": "params_shard_91.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e5284be48bccc8e3f5097e046ca92303" | |
| }, | |
| { | |
| "dataPath": "params_shard_92.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c4c534a0ef9463127001f94b59fb0073" | |
| }, | |
| { | |
| "dataPath": "params_shard_93.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.29.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.29.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.29.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "a395082d51edd745ae46d749d843c258" | |
| }, | |
| { | |
| "dataPath": "params_shard_94.bin", | |
| "format": "raw-shard", | |
| "nbytes": 23527424, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 1436 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 23527424, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6e479e52f575647f5ce4d677ba8d12d8" | |
| }, | |
| { | |
| "dataPath": "params_shard_95.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "12bbbf4a85465f7871eac1f287294c4e" | |
| }, | |
| { | |
| "dataPath": "params_shard_96.bin", | |
| "format": "raw-shard", | |
| "nbytes": 27848704, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.30.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 359 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2940928, | |
| "byteOffset": 18993152 | |
| }, | |
| { | |
| "name": "model.layers.30.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 21934080 | |
| }, | |
| { | |
| "name": "model.layers.30.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 27840512 | |
| } | |
| ], | |
| "md5sum": "dc4f7d5fa7d1edaa72c4fa5aa953edb5" | |
| }, | |
| { | |
| "dataPath": "params_shard_97.bin", | |
| "format": "raw-shard", | |
| "nbytes": 47251456, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 28672, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 47251456, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "091aa9f037c32414f9848f162bbdb276" | |
| }, | |
| { | |
| "dataPath": "params_shard_98.bin", | |
| "format": "raw-shard", | |
| "nbytes": 24891392, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| }, | |
| { | |
| "name": "model.layers.31.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 28672, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 5906432, | |
| "byteOffset": 18984960 | |
| } | |
| ], | |
| "md5sum": "60ae2443d66d2a561a3425c0c270d987" | |
| }, | |
| { | |
| "dataPath": "params_shard_99.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18984960, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.self_attn.qkv_proj.q_weight", | |
| "shape": [ | |
| 6144, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 10125312, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.qkv_proj.q_scale", | |
| "shape": [ | |
| 6144, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1265664, | |
| "byteOffset": 10125312 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 4096, | |
| 412 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6750208, | |
| "byteOffset": 11390976 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 4096, | |
| 103 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 843776, | |
| "byteOffset": 18141184 | |
| } | |
| ], | |
| "md5sum": "0e985b0c456f0a98d34cc57f23d4b319" | |
| } | |
| ] | |
| } |