| { | |
| "metadata": { | |
| "ParamSize": 210, | |
| "ParamBytes": 10457367552.0, | |
| "BitsPerParam": 32.0 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 1179648000, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "shape": [ | |
| 256000, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1179648000, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "62204215d5097751ae26290c6bb95b96" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c763984f66d00a44b61d9d51bb02cae3" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3bdc8fa3b17a013ac90cc3f7e8c224f5" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5f67ca7508419bf6966c9e97e8aaf527" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "90430c831dbbf4e397210bc71f7f8d64" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "de11a3b74f47ba1430cea747c85a6329" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28348416, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 4608 | |
| }, | |
| { | |
| "name": "model.layers.0.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9216 | |
| }, | |
| { | |
| "name": "model.layers.0.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 13824 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 18432 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 18892800 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 28329984 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 28334592 | |
| }, | |
| { | |
| "name": "model.layers.1.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 28339200 | |
| }, | |
| { | |
| "name": "model.layers.1.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 28343808 | |
| } | |
| ], | |
| "md5sum": "2802701476a76506baf97b06bba0f746" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a86ababa0fb0ead8224dbe57698dc227" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e0e9c4c093911fd7761bc8c88618ca3d" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.10.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.10.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "b3ee22d2770fb9b93347bac59152fdb0" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "104cd3f16f8c0deccdb79139a4d2631b" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8b2e52123607a5ff981b62fda42f3f42" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.11.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.11.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "fcbcea3d3de6a1b10e491e7a44740f14" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "026c0a4793b398dcc65c7af9ae0f39d5" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7f0f493c428fa02b1851b8ac5d56cbce" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.12.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.12.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "5af70b42143c0a2f287bf3cd2548c747" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9216c08b71172fc715210037e81a0411" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7e8664fb062a5434da3e1d2ee5b9ad9b" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.13.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.13.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "1c5ed6a38c2cadc96100180521a0d678" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "88225258d479cb2800e6a9d7316aae6c" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8f2fafa637abea77ee1ba268c1575e56" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.14.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.14.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "150300b9bda9b6184ac2b7174ab47322" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2139b50f9876756a97d4d4def69b4b6d" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c36aa796e244e0883c9235aabff09488" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.15.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.15.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "cd6e2f65f8ce9520f67b6948e061f7f5" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e50de57dafc9d753b74392d35d92b04f" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7228aa52df7bf064e322299345dbc98e" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.16.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.16.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "773544624d07ead5a304cc9278eacb6c" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b115593000e031367512ff2a2bef0dab" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1aeb084857b23899155a47aa17ce1374" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.17.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.17.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "cdc753982202900bf9c850174d7a8525" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "29cc3d52a9e33240234b71c0bdeea9a7" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d13fb9f509d99fc103a7224473d6bf65" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.18.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.18.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "f7175237b75ad08b569dbcdf61c1ffff" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5fedcaa2e76818925314847463f92706" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d61ef76e5d20fcf58d3428f857f39ed9" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.19.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.19.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "84a15de2559c5df3e11509196fda3730" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d5e1b0beb311ea7cae3454052509c21e" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "80617fc9a55f8437fb2c374013b3ffd7" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.2.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.2.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "e50bf9d12b20717933715e74cbeedd6b" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "99a08e5a05761c33a3c57754d1391745" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5a0ea983928acba60569714fbf50079c" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.20.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.20.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "73942feec2c47358cbf0dfab58d14bd6" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "dbe4a8f46fd21d8bf21625a916637eea" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "27f6c56977a3d53f12f517c33a7ae45d" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.21.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.21.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "59e5c0cb1381e8c78d816b3ec492ec5e" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d823340637874eaff98864500b40e983" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5add29e1699e76e24e95bfdfb1d6f466" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.22.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.22.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "712c4ea3c91ee3a0b3cf17b44d2d5fd9" | |
| }, | |
| { | |
| "dataPath": "params_shard_49.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "94485ce84c951931a96a7dd600be609a" | |
| }, | |
| { | |
| "dataPath": "params_shard_50.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4e6767a86c6289ddafefb902fb311890" | |
| }, | |
| { | |
| "dataPath": "params_shard_51.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.23.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.23.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "af0fff5969b256b9d7391b3907ae4839" | |
| }, | |
| { | |
| "dataPath": "params_shard_52.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b4e94b9873512cc6b3535fe2028988f7" | |
| }, | |
| { | |
| "dataPath": "params_shard_53.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28311552, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9437184 | |
| } | |
| ], | |
| "md5sum": "942bbbcb26ca333824d079fc5351313b" | |
| }, | |
| { | |
| "dataPath": "params_shard_54.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5c99e916ea1e05424fad902d8fca3255" | |
| }, | |
| { | |
| "dataPath": "params_shard_55.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c58faf8bfe09b4135fc2341d827c0f56" | |
| }, | |
| { | |
| "dataPath": "params_shard_56.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.3.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.3.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "5d260f2ade30fb5ad195cee460c3e83f" | |
| }, | |
| { | |
| "dataPath": "params_shard_57.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cbd746232d67e9b597ed8ef5b6f0c89b" | |
| }, | |
| { | |
| "dataPath": "params_shard_58.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2c7ae43950657786930cd79027138869" | |
| }, | |
| { | |
| "dataPath": "params_shard_59.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.4.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.4.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "029f24d418ff2b2a502d6e5c49670798" | |
| }, | |
| { | |
| "dataPath": "params_shard_60.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "61f71048d0529605f7ac20601cc0fdce" | |
| }, | |
| { | |
| "dataPath": "params_shard_61.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "15c5279bf3da9f6f8d165e2b7d98b768" | |
| }, | |
| { | |
| "dataPath": "params_shard_62.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.5.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.5.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "175bd30e9196e7eb4cc742e6ff9916e6" | |
| }, | |
| { | |
| "dataPath": "params_shard_63.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cb46a0804e54e366b949a6857c2a8f45" | |
| }, | |
| { | |
| "dataPath": "params_shard_64.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a8397b6a4bf904a8c9f23e8fde4ef3b4" | |
| }, | |
| { | |
| "dataPath": "params_shard_65.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.6.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.6.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "5d57b4f7c069864b369feea71009a785" | |
| }, | |
| { | |
| "dataPath": "params_shard_66.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8d5477556d97018c91402179bc28d25e" | |
| }, | |
| { | |
| "dataPath": "params_shard_67.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "777c4af18d26abac1975eef88e2bc984" | |
| }, | |
| { | |
| "dataPath": "params_shard_68.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.7.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.7.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "787dab15288956bb41ead752a08355ad" | |
| }, | |
| { | |
| "dataPath": "params_shard_69.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "adfd9c0cb3363492b0a80916becbaed1" | |
| }, | |
| { | |
| "dataPath": "params_shard_70.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c760588decd97f1bf41973802d3c3624" | |
| }, | |
| { | |
| "dataPath": "params_shard_71.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.8.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.8.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "3ff1d1d3e15343053b4a7ec38b169e55" | |
| }, | |
| { | |
| "dataPath": "params_shard_72.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b9f576137fb67786e3a745aa951f64bf" | |
| }, | |
| { | |
| "dataPath": "params_shard_73.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cb92beeb40aa2ec7eb1e3c7b8c6f42d6" | |
| }, | |
| { | |
| "dataPath": "params_shard_74.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28329984, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.9.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.9.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9455616 | |
| } | |
| ], | |
| "md5sum": "b80587270e3afff1e7bbb68d85f58aba" | |
| }, | |
| { | |
| "dataPath": "params_shard_75.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "52f57bf19dee44be665a7e35807b7530" | |
| }, | |
| { | |
| "dataPath": "params_shard_76.bin", | |
| "format": "raw-shard", | |
| "nbytes": 42467328, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.down_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 9216 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 42467328, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5910b60613c521066a125487522f1815" | |
| }, | |
| { | |
| "dataPath": "params_shard_77.bin", | |
| "format": "raw-shard", | |
| "nbytes": 84934656, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 18432, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 84934656, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "688b1a1935ec355712b70083b6b1af9d" | |
| }, | |
| { | |
| "dataPath": "params_shard_78.bin", | |
| "format": "raw-shard", | |
| "nbytes": 28348416, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9441792 | |
| }, | |
| { | |
| "name": "model.layers.24.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9446400 | |
| }, | |
| { | |
| "name": "model.layers.24.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9451008 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9455616 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9460224 | |
| }, | |
| { | |
| "name": "model.layers.25.post_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9464832 | |
| }, | |
| { | |
| "name": "model.layers.25.pre_feedforward_layernorm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9469440 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.qkv_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 9474048 | |
| } | |
| ], | |
| "md5sum": "3c384d20a4c9619a47e975a21c8666a0" | |
| }, | |
| { | |
| "dataPath": "params_shard_79.bin", | |
| "format": "raw-shard", | |
| "nbytes": 9441792, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.weight", | |
| "shape": [ | |
| 2304, | |
| 2048 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 9437184, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 2304 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 4608, | |
| "byteOffset": 9437184 | |
| } | |
| ], | |
| "md5sum": "363eeb447d8c8d38d31c3f544cbfee83" | |
| } | |
| ] | |
| } |