| { | |
| "metadata": { | |
| "ParamSize": 313, | |
| "ParamBytes": 4760885248.0, | |
| "BitsPerParam": 5.0011817065612245 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 272498688, | |
| "records": [ | |
| { | |
| "name": "lm_head.q_weight", | |
| "shape": [ | |
| 152064, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 272498688, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "83b87b6cdbf7c228e43a9c35b122ff72" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 34062336, | |
| "records": [ | |
| { | |
| "name": "lm_head.q_scale", | |
| "shape": [ | |
| 152064, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 34062336, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f5e00254f2ace7b2b05a1b3812d67a81" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "73ae3acb9123c6fd1843ed6a7fa937ca" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d77d52fb1f03284902aedbedacacfa5b" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1a65fabd9c73de9124cbbc685dcb8a35" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "45c096045117ccdd2b0f0b648a3f7f9b" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33519616, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 4243456 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 4250624 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16980992 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 16988160 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 16997376 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 25254912 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 26287104 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 32709632 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 33512448 | |
| } | |
| ], | |
| "md5sum": "1533ad4b72c7b62ffdef7a24a0284d58" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a9445d750e8afff77fd0a6f21f5f5d68" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9d864e8bebe798630d7ba91e2f205459" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8d399cd1efac964d1703c602e31f4b9a" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33512448, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 4243456 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 12730368 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 12737536 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 12746752 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 21004288 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 22036480 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 28459008 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29261824 | |
| }, | |
| { | |
| "name": "model.layers.25.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 29268992 | |
| } | |
| ], | |
| "md5sum": "03dfff3930c0943fd5bb2fa8110b41d0" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "72152b59f1743474def2de28be396e51" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4f467d3bd79a084cb9d673bb4bc33d57" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.26.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.26.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "1a8d319d7ad212724cb8954d0e1db87c" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "544eb7fd835fc9306f05eb1c7d47049e" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cf71245e25b7cf9aa1b9d2040b3daf3c" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.26.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.27.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.27.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "2c439dd7bdf245da5724485287137f8b" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 272498688, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_weight", | |
| "shape": [ | |
| 152064, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 272498688, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5ab53cf9b8e920d2d82025004f6afbca" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 34062336, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.q_scale", | |
| "shape": [ | |
| 152064, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 34062336, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b3e8cf13c1c5d80e9366323286ac7af7" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5de1fee5c482d3148b414c0d24ec16db" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f32a4835d9a3028782e018f7c64897e7" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29276160, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.27.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25025536 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25032704 | |
| } | |
| ], | |
| "md5sum": "876b391770314335a0beaf77ba08d186" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "07d8a0bd117f095e514cdc2124f4f81f" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fa3b38f7e9070b5389e40abcb7e0818d" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "47461506f75f2669ea6aaebe17251de1" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3d892875c50e02e1262988e5b9824f56" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e707a1016d55a83a47450eefa4d9c97b" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "3cf389d7e20d4543efe6bf00ebbffd28" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f293348282e2560598b7d1301acd2e8c" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d5a0ecbc0f543232c42c67715ba5e298" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "d34e8f637ba42d08cd7c02bc3d9fdb42" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "113a04c3692ed355b50d5a6a8a68dac4" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1505f0e77f236d540c880d4711ec7672" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "efafbfbb53ac516ea26e5d0363cb9716" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5f5ab8e687c5a39e0d8cc44b697bd9a6" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "995b4aeb04e50d4b574ed38e49283c30" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "24c77ee139649ba7247c53f39e64bb98" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33299456, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8486912 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 8494080 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 8503296 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 16760832 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 17793024 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 24215552 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25018368 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25025536 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 25032704 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 25041920 | |
| } | |
| ], | |
| "md5sum": "cad1c081de332ee46c9170c248f04af1" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4948558d39b01aca9a9bb8d4082293ea" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "666ea503986c303306e0117e6ec9d4e1" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 30301184, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 1032192 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 7454720 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 8264704 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 12508160 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 20995072 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 21002240 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 21011456 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 29268992 | |
| } | |
| ], | |
| "md5sum": "fcde6e209a600b680e3e106ee36c05c7" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7d28016730dba7eb67ed00c7d18e2a32" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4bcb4631bb433331e4f9ade45b655858" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 7225344 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 7232512 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 11475968 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 19962880 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 19970048 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 19979264 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 28236800 | |
| } | |
| ], | |
| "md5sum": "7865a4540b5410dfddb39c14c1f71293" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5c120d2db49718cd70308abe1f0a7c17" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f6d25e8893306ffa9029e1628bf8e747" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 7225344 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 7232512 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 11475968 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 19962880 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 19970048 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 19979264 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 28236800 | |
| } | |
| ], | |
| "md5sum": "e8123315cfea4dce5540948f1c58af62" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f4c0c302b7e02ccfc12ed8b4564cee80" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ca7bcc2790d275b21d5d75bbb1393c30" | |
| }, | |
| { | |
| "dataPath": "params_shard_49.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 7225344 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 7232512 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 11475968 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 19962880 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 19970048 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 19979264 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 28236800 | |
| } | |
| ], | |
| "md5sum": "a717d6ee48bc94793e61e6d915fa88fc" | |
| }, | |
| { | |
| "dataPath": "params_shard_50.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "494bf7d41c26175e5cc0d8d4a3c69fc1" | |
| }, | |
| { | |
| "dataPath": "params_shard_51.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "894711d1fabeaadec8ea2e63e82c49ce" | |
| }, | |
| { | |
| "dataPath": "params_shard_52.bin", | |
| "format": "raw-shard", | |
| "nbytes": 32250880, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 6422528 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 7225344 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 7232512 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 15719424 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 15726592 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 15735808 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 23993344 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 25025536 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 31448064 | |
| } | |
| ], | |
| "md5sum": "35ace4510a01c5ca589d07e57dee5089" | |
| }, | |
| { | |
| "dataPath": "params_shard_53.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "81055182987d47764966e1e886ac616b" | |
| }, | |
| { | |
| "dataPath": "params_shard_54.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "91d132fe6f26c87d313fa44e1374cf0b" | |
| }, | |
| { | |
| "dataPath": "params_shard_55.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a57601f9dd90395ba6a0bc795fb37416" | |
| }, | |
| { | |
| "dataPath": "params_shard_56.bin", | |
| "format": "raw-shard", | |
| "nbytes": 25484288, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 4243456 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 12730368 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 12737536 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 16980992 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25467904 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 25475072 | |
| } | |
| ], | |
| "md5sum": "7da2a17523ced8c67ae2b4b6e92a578a" | |
| }, | |
| { | |
| "dataPath": "params_shard_57.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "42cb7d52fcacb9a281650e5142802a70" | |
| }, | |
| { | |
| "dataPath": "params_shard_58.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ab89c5583ada89a6dfcffce4b61233ed" | |
| }, | |
| { | |
| "dataPath": "params_shard_59.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "15d57961e9eee93491d1b6f9dc6524c8" | |
| }, | |
| { | |
| "dataPath": "params_shard_60.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4802e66c626418da28a658f311fbaa97" | |
| }, | |
| { | |
| "dataPath": "params_shard_61.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0160dd8d67975dec8549965ef6be8a30" | |
| }, | |
| { | |
| "dataPath": "params_shard_62.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "fb637cb2f5ba0921a09715f9d64166bc" | |
| }, | |
| { | |
| "dataPath": "params_shard_63.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4bf4b84dbd451b0dba8c9133f2ae277b" | |
| }, | |
| { | |
| "dataPath": "params_shard_64.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "88b1d4db154260f446ab82d25c70f075" | |
| }, | |
| { | |
| "dataPath": "params_shard_65.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3ea6473cb073a53c9aa1069419f23846" | |
| }, | |
| { | |
| "dataPath": "params_shard_66.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33512448, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 20758528 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 25009152 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 33496064 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 33503232 | |
| } | |
| ], | |
| "md5sum": "3d6d7b9027f18e08cf2626ed428fbb64" | |
| }, | |
| { | |
| "dataPath": "params_shard_67.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bdb615e2969029886cd79d6ded703ec0" | |
| }, | |
| { | |
| "dataPath": "params_shard_68.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "56e43c4c1c07a1f2e3b8724f936013b3" | |
| }, | |
| { | |
| "dataPath": "params_shard_69.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "17a5f79dcf628fb355720e306bc8d7b4" | |
| }, | |
| { | |
| "dataPath": "params_shard_70.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e5c9b7359c4a6c341e5e9561b3af0c74" | |
| }, | |
| { | |
| "dataPath": "params_shard_71.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9aab43017bbf1e3268be8b1e18e2ab1c" | |
| }, | |
| { | |
| "dataPath": "params_shard_72.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "05016f5523aa66b2863acaae40e78f8c" | |
| }, | |
| { | |
| "dataPath": "params_shard_73.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7747918e3f88468c1cdc8da7e358c022" | |
| }, | |
| { | |
| "dataPath": "params_shard_74.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "672eddc1c05403869307c98865dc28a8" | |
| }, | |
| { | |
| "dataPath": "params_shard_75.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "64b7e932292d3a0d8aaef2086eb0c984" | |
| }, | |
| { | |
| "dataPath": "params_shard_76.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b100b0049434657ea453f0c4f9bd5573" | |
| }, | |
| { | |
| "dataPath": "params_shard_77.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3a16b177a1771df6c5561a31d7ee36c4" | |
| }, | |
| { | |
| "dataPath": "params_shard_78.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "075a04f384c8b972a989a1c6f3bf438b" | |
| }, | |
| { | |
| "dataPath": "params_shard_79.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "16a60689505295e179f076d6f2e9657c" | |
| }, | |
| { | |
| "dataPath": "params_shard_80.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bdeccc31ded72d0b078fb806735164bc" | |
| }, | |
| { | |
| "dataPath": "params_shard_81.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "c4bc4d11fe41e0daaf22560a7ac22631" | |
| }, | |
| { | |
| "dataPath": "params_shard_82.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33947648, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 2368 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33947648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "698b00e52b6c47caf892f56e38cc342f" | |
| }, | |
| { | |
| "dataPath": "params_shard_83.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "53da982e156c7f796e0b203295bfb116" | |
| }, | |
| { | |
| "dataPath": "params_shard_84.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29268992, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.down_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 592 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 4243456, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 20765696 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 29252608 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 29259776 | |
| } | |
| ], | |
| "md5sum": "0fa931510f181da0fd5b1083e51c55d4" | |
| }, | |
| { | |
| "dataPath": "params_shard_85.bin", | |
| "format": "raw-shard", | |
| "nbytes": 67895296, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_weight", | |
| "shape": [ | |
| 37888, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 67895296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "36ab6f8ffbb1a84b0062a173931f0615" | |
| }, | |
| { | |
| "dataPath": "params_shard_86.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33283072, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 8257536 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 9289728 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 15712256 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 16515072 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.q_scale", | |
| "shape": [ | |
| 37888, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 8486912, | |
| "byteOffset": 16522240 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3584 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 7168, | |
| "byteOffset": 25009152 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.bias", | |
| "shape": [ | |
| 4608 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 9216, | |
| "byteOffset": 25016320 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.q_weight", | |
| "shape": [ | |
| 4608, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8257536, | |
| "byteOffset": 25025536 | |
| } | |
| ], | |
| "md5sum": "8d25b84ff4ecb946793076452458df5e" | |
| }, | |
| { | |
| "dataPath": "params_shard_87.bin", | |
| "format": "raw-shard", | |
| "nbytes": 8257536, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.q_scale", | |
| "shape": [ | |
| 4608, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 1032192, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_weight", | |
| "shape": [ | |
| 3584, | |
| 448 | |
| ], | |
| "dtype": "uint32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6422528, | |
| "byteOffset": 1032192 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.q_scale", | |
| "shape": [ | |
| 3584, | |
| 112 | |
| ], | |
| "dtype": "bfloat16", | |
| "format": "raw", | |
| "nbytes": 802816, | |
| "byteOffset": 7454720 | |
| } | |
| ], | |
| "md5sum": "b3d5321b285d2f26218b0d85e99ba140" | |
| } | |
| ] | |
| } |