| { | |
| "metadata": { | |
| "ParamSize": 170, | |
| "ParamBytes": 988065536.0, | |
| "BitsPerParam": 16.0 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 272269312, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "shape": [ | |
| 151936, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 272269312, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9c2276977b80f698556816421622352a" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826560, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 1792 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8718080 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26152448 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26154752 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28219136 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29824768 | |
| } | |
| ], | |
| "md5sum": "7aa56db3316a36fecc827f1134159fc3" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "6a00a74fef6caa9f59a24baef57bdc2c" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "9be229aa9f9c26442c7d3e7fbc17db2a" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "6e4cdce7c71f7b492b9bc49e2439a98c" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "6b0de293079e94b9ce911a65aee7a5e9" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "1bf604b0bac97f358a181e4e4ba49221" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "7334eab63e02a09754db7edb4c2c79dd" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "f574d5bc202cdc1aa7355bee5a80e934" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "a800722636660cd9819c90c6a2ec1bad" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "561af8229f6721c9fd16f4bfbdbe2a96" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "10b83f14823650721c5941737a814795" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "5ee494b14573733f13c47ff6d3d22242" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "69d2cb1700a3a4d56e3722db3380bff2" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "d9c2d36676d974f8ec6cdd67bacb136e" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "c628deff33f36f21c9945aa36af0f699" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "68476d60f51c53fec003188a0bae8ee3" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "df7593f2d9cfc7fdc887c46a2fee65e9" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "706df355d9a7994a83c46f474eee6c58" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "7c36e162780e0fdc0a6a9b9e96f046bc" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "1e6fbc4dc336e8b61a046012e748bf24" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "ce22bf370a3ac8ba1094ae6182ccbf70" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "0bcd63a0a9528474d6a658ea2ca51791" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "942964c7522bbfe279b32d0a32715ab2" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "106f860dac3f9d6186f6cfcc61be8722" | |
| } | |
| ] | |
| } |