| { | |
| "metadata": { | |
| "ParamSize": 170, | |
| "ParamBytes": 1976131072.0, | |
| "BitsPerParam": 25.087060952233546 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 272269312, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "shape": [ | |
| 151936, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 272269312, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2c7d75cb46fae8e938c346f16a4dfff1" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826560, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 1792 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8718080 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26152448 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26154752 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28219136 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29824768 | |
| } | |
| ], | |
| "md5sum": "df1061d2a8a37ef9bc8152e453a2d900" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "873f60f8ac673715ebd2a7259fa2c329" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "5f75415c55ef64daa71cf3855cbbd952" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "3ba414bb702d78d19a0f0c9556ee3551" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "359d8a4e4dd73ccb8707c5a80048b41f" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "e05e7ffb7a697f4e9d76b9d0eefb8d72" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "f04c661d07f9f8e0fa520ceebcbdf6f6" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "0912701565163822366adc5dcd3c95af" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "232d5abeb6db622e9d2ca8aa7d4f1afd" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "aa2db6de9df54c6cf51afaf2a5f55861" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "9d67aa6641e2b8c9da3ffcd92ace2c58" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "34b1f260fd0452c6c08d4ab5ceee97f3" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "a3b279fb77ad69b700f20c1613677e28" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "1ab513d8d5eeda78167c7141dcb59bfb" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "81f0981e0dd693904ff9317b56b45ff1" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "0ec718df652f9e704128de447f0ce79e" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "9744ea23cfc76fcc7a59113f5287c695" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "2b0f7c4bc164777d7ee273ca73013255" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "1488235bcf2bf4c4101044be7999463a" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "c88f067abace63e48f37146b8f16c702" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "373dd2ad8ec1bdd05e895040c78a2f87" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "6fcc885bde415023ade9c3ee57cfca96" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "88eac06c4e04dbd9d3286d386eb0c7dc" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "6ad2594c5127ba09729bea482f2cb4b7" | |
| } | |
| ] | |
| } |