| { | |
| "metadata": { | |
| "ParamSize": 291, | |
| "ParamBytes": 16381470720.0, | |
| "BitsPerParam": 16.0 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 1244659712, | |
| "records": [ | |
| { | |
| "name": "lm_head.weight", | |
| "shape": [ | |
| 151936, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1244659712, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c5dae1d3cb6596a30dcbee1ba7f7647a" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 1244659712, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "shape": [ | |
| 151936, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1244659712, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6462f41e5b85dfba641fc2eb14e3a443" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a24c65269b2fb92dbf9f739a3c3797be" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "de3ca647e004b09740d9b7214e916346" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f28b8d26239b50d0bfcfd7d66d69f527" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8a7e488560bad907b7da27bd4d8f5116" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bd36f0ac102a7910d4d331775beb18a5" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "82a7f33315ef0d53bde759677571cfe8" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e474c9bdbb38c71fe0a3810c09a503e4" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "333bcb09b8008f0304fffd3f4c3632ea" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "74b2bb7039cff65a87b991174121bfc3" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "161eee515959542a4436efc2a4cdb992" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b608e3b33be2a12de0e2ff2487558fbf" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c9198aaa3aea4a04736780cb1c1676cb" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "205101e40c7a9e977a0b54302c4fc69f" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "99f713dc77ca075af9a5cd58b9b3e93b" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ecf25ae851095bb1a081f9e8db3c7c3c" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "648b8ddc636d26866c03f00f338cf7bd" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "893cccd9a7c344ee0b8250427f7fcd52" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f3b88132d80699aa948ace1c8adfc610" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fedb2adca6e168fe2c0959891a8df83c" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "742ecb4c76202a55ed6bfff3ce43f5a5" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "111106346aa0496d17f9ed001979f216" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "41ee309bcec45ae84c835e3deb7abb82" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "17c0164e52dfae7e55ab6dafe0de7941" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8d5b2296727d56028d6964a10b7033e4" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7746ab534b43039fb7e741e8765dfacc" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "83816c092168f22608746f9ed734f558" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5f68dca716c2fba210fe0b16a9a0e4bc" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ef3c273a4a5889a1b17d2bf8f8d43d6b" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ebff226fe710556a72633c0c37ca963f" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "68792ff0e9953f5a7645ace185fcdd8f" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2c433187467a32b41a9e75ff35c7fce3" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3583e3ed9467c307ef9c3cacc27fd87a" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "17555c10d7a55f39252aa4d8c5f5ba48" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c0561b5338e2041fcfb8434be90dc0c8" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f0d7ff0e37dba39dbe156e1be60fe570" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7adbad0f32cd60c6ae02af7720be6095" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5e9dfc3c36282db900169c86b757c764" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9233fede931cf9d4d435d7e73f5a6a3c" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9f2d9f5b78af646e8353045e9937965e" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4ed437d57677a7d3ab511db83534b90f" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d7664db93e5e5f2173d98d3dcbd56159" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ca3c9d3b05886b6e925ed69a60ea047c" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b9722baf10d743ead6cb7163e7c8e607" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e01dafcbd12cd1d1793c44ecc1ddc090" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "361036040c23cdd749ae6efa389b81ee" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d95fe72bd4e1110fa96ed271ed5562ca" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ee3a63812c933fb96c5faab9844a38bc" | |
| }, | |
| { | |
| "dataPath": "params_shard_49.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1b24b8d396185580c07ab18019bda079" | |
| }, | |
| { | |
| "dataPath": "params_shard_50.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fca3717951ec0fa873e60a97a36f32c3" | |
| }, | |
| { | |
| "dataPath": "params_shard_51.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bff80101c18cd5c691ec017bb4860d9b" | |
| }, | |
| { | |
| "dataPath": "params_shard_52.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "41405e4dd3e361b5ce03c383039aa26f" | |
| }, | |
| { | |
| "dataPath": "params_shard_53.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "dfb501a3125fe97a24090cee218dd35d" | |
| }, | |
| { | |
| "dataPath": "params_shard_54.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a7f1ad079c59027d3f39f064074caf19" | |
| }, | |
| { | |
| "dataPath": "params_shard_55.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "98193397634dd48ff19e17629bcacc37" | |
| }, | |
| { | |
| "dataPath": "params_shard_56.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bea2ae380c43aac89fda3813a1f9e0b0" | |
| }, | |
| { | |
| "dataPath": "params_shard_57.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9f8ec78db3860c067e1228bfb592bf86" | |
| }, | |
| { | |
| "dataPath": "params_shard_58.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d4efde345fd798b798997fd825f7f175" | |
| }, | |
| { | |
| "dataPath": "params_shard_59.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e7c01851628d35e56e809009ac09f6c1" | |
| }, | |
| { | |
| "dataPath": "params_shard_60.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a01fd16fe37952bc5d8ec49ee942a291" | |
| }, | |
| { | |
| "dataPath": "params_shard_61.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5bff154b3e4cf5e7e30bc164ed8ff6f1" | |
| }, | |
| { | |
| "dataPath": "params_shard_62.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "efd9123ddf7ff1873cd649c52383a123" | |
| }, | |
| { | |
| "dataPath": "params_shard_63.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "99302bfe4deaa06108ab1a5b60da0848" | |
| }, | |
| { | |
| "dataPath": "params_shard_64.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4a166663530a4379e1329416e52cb7c2" | |
| }, | |
| { | |
| "dataPath": "params_shard_65.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ed2977dee4bf13a5389fd2ddefd496bb" | |
| }, | |
| { | |
| "dataPath": "params_shard_66.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "10d5cea6c6ae28ffe81f5483aa77eb06" | |
| }, | |
| { | |
| "dataPath": "params_shard_67.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "51b04907dcae2c50ba6aeab7ca737859" | |
| }, | |
| { | |
| "dataPath": "params_shard_68.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d4af7c7fde51470dadb20340265acd11" | |
| }, | |
| { | |
| "dataPath": "params_shard_69.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "950d7bd87d70e6b7c86e471e97786b4c" | |
| }, | |
| { | |
| "dataPath": "params_shard_70.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "32d89c0b5182c550a0f3b41a0bd6c30e" | |
| }, | |
| { | |
| "dataPath": "params_shard_71.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d312ef9e50c8a6902483ed8d7a2210a5" | |
| }, | |
| { | |
| "dataPath": "params_shard_72.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8818d518e818aa2d880608949e6c4a46" | |
| }, | |
| { | |
| "dataPath": "params_shard_73.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fd9466323576d738cce524b7b0992cc9" | |
| }, | |
| { | |
| "dataPath": "params_shard_74.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "63ecabc9f82cd0c825dd770bc1d021be" | |
| }, | |
| { | |
| "dataPath": "params_shard_75.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e4855851ec9d572f20d0aea506ebd97c" | |
| }, | |
| { | |
| "dataPath": "params_shard_76.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ed1c56bd6fab914ca3fb4e73aa15dd8e" | |
| }, | |
| { | |
| "dataPath": "params_shard_77.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "52a30f47109ee91530538151ab61c7d9" | |
| }, | |
| { | |
| "dataPath": "params_shard_78.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "58fb52ff03604acae35e163da46bacf5" | |
| }, | |
| { | |
| "dataPath": "params_shard_79.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "294fc17db81ff23728a2439e81d54d48" | |
| }, | |
| { | |
| "dataPath": "params_shard_80.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4532c6092ff2bf753fc8eba3782c6ace" | |
| }, | |
| { | |
| "dataPath": "params_shard_81.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f28529666f0a81df699c043b653313a8" | |
| }, | |
| { | |
| "dataPath": "params_shard_82.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3c978a04ecbb988be45d4181bbe2cf61" | |
| }, | |
| { | |
| "dataPath": "params_shard_83.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d9ac1c7807429e06efdf1b5099410e25" | |
| }, | |
| { | |
| "dataPath": "params_shard_84.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c4ad1ab7f9769e0ba67ccaa31d921f45" | |
| }, | |
| { | |
| "dataPath": "params_shard_85.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "da6a1c64ec4b25d48baae1f6d34ff61a" | |
| }, | |
| { | |
| "dataPath": "params_shard_86.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "15d7a79a8de2b27dcef8650d5d4d5356" | |
| }, | |
| { | |
| "dataPath": "params_shard_87.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "93cccf81ca762a458bbb225835c6d85c" | |
| }, | |
| { | |
| "dataPath": "params_shard_88.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "faf88db6afd7f56e6810901b1f60e1dc" | |
| }, | |
| { | |
| "dataPath": "params_shard_89.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "238bb0d037a7be25b4f61e6c1342715f" | |
| }, | |
| { | |
| "dataPath": "params_shard_90.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "821b213c2045480f566c027a238364d2" | |
| }, | |
| { | |
| "dataPath": "params_shard_91.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "13181a12fb4406b68f80dd40a7b9d4df" | |
| }, | |
| { | |
| "dataPath": "params_shard_92.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1e74230a8a3f3c7947f2a65d329a5854" | |
| }, | |
| { | |
| "dataPath": "params_shard_93.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f81575a0f04118ffc2e2e14dba5f9c8b" | |
| }, | |
| { | |
| "dataPath": "params_shard_94.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8bd82cc9cc8090d01901c66b4e3f04e0" | |
| }, | |
| { | |
| "dataPath": "params_shard_95.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eecdc2a4ae135fa97c8a62e73040c095" | |
| }, | |
| { | |
| "dataPath": "params_shard_96.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c74ba4806850b6a7b1634779eca0b03b" | |
| }, | |
| { | |
| "dataPath": "params_shard_97.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "641e8bfe58c56481fd22315b9da01663" | |
| }, | |
| { | |
| "dataPath": "params_shard_98.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "baa4347d5f105d8c4d9936aa72308892" | |
| }, | |
| { | |
| "dataPath": "params_shard_99.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3554cf7d8a5e2cfd1fc8e87422c2a5a1" | |
| }, | |
| { | |
| "dataPath": "params_shard_100.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7006d334eada2b72130f9ca52ba0bcad" | |
| }, | |
| { | |
| "dataPath": "params_shard_101.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.24.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a64ce69101547f83ecf4415f1c2351c8" | |
| }, | |
| { | |
| "dataPath": "params_shard_102.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5f73d1d5f43a32670136f8f01ea79ca1" | |
| }, | |
| { | |
| "dataPath": "params_shard_103.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "758773e88ff65948b975cee638b2442e" | |
| }, | |
| { | |
| "dataPath": "params_shard_104.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "42600c06ebef3b03fde776c0ebadac93" | |
| }, | |
| { | |
| "dataPath": "params_shard_105.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.25.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "687bfb9ed304fab9befe9bca23fc2acd" | |
| }, | |
| { | |
| "dataPath": "params_shard_106.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bbfe00fee9d78b4b120d62fd49a1040a" | |
| }, | |
| { | |
| "dataPath": "params_shard_107.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "86c3c9e55fd015547d63e853a806561d" | |
| }, | |
| { | |
| "dataPath": "params_shard_108.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "23112ed61d7c01199af0047cca8566f8" | |
| }, | |
| { | |
| "dataPath": "params_shard_109.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.26.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e79d77ae46bc62698aaf5b5abc727ece" | |
| }, | |
| { | |
| "dataPath": "params_shard_110.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "01f06e775c55ec2dce796c4df693a648" | |
| }, | |
| { | |
| "dataPath": "params_shard_111.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "526136e9889804940c032bebacad4be3" | |
| }, | |
| { | |
| "dataPath": "params_shard_112.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "371ac4900715aed71da73cda109bac33" | |
| }, | |
| { | |
| "dataPath": "params_shard_113.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.27.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "656cab179c5a61da4611705d6e7e9afa" | |
| }, | |
| { | |
| "dataPath": "params_shard_114.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2c7c1eaa0fc5102d4fb68472cb96a1eb" | |
| }, | |
| { | |
| "dataPath": "params_shard_115.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "17728de8fd4780000d37e30d34883ca1" | |
| }, | |
| { | |
| "dataPath": "params_shard_116.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7e19ea8cc3c963f36be67092e1729755" | |
| }, | |
| { | |
| "dataPath": "params_shard_117.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.28.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f3f1ab45a4aabc6c103dce337589b08b" | |
| }, | |
| { | |
| "dataPath": "params_shard_118.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b71d94f83c3c4a4435b49309eee73264" | |
| }, | |
| { | |
| "dataPath": "params_shard_119.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ab66806d66bbb7bc35ce02300f04045e" | |
| }, | |
| { | |
| "dataPath": "params_shard_120.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f1da4fc39a65a11625cd65f0e63633c8" | |
| }, | |
| { | |
| "dataPath": "params_shard_121.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.29.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9f7d1b6d54d92ede5c4e7571538270f2" | |
| }, | |
| { | |
| "dataPath": "params_shard_122.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6ea234a16e7477f03017c7e3b0de5092" | |
| }, | |
| { | |
| "dataPath": "params_shard_123.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eea523e3a0b22f84f0a93e7f0bd30dfe" | |
| }, | |
| { | |
| "dataPath": "params_shard_124.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eec98a4bae0541be73132abad74918a4" | |
| }, | |
| { | |
| "dataPath": "params_shard_125.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.30.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "60c33e50c2b436aecaa3947153e18e27" | |
| }, | |
| { | |
| "dataPath": "params_shard_126.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8ba2a1c70adbe336fdea471452e598f9" | |
| }, | |
| { | |
| "dataPath": "params_shard_127.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c5b5d3ce1e0615348f7aa22582bc1db4" | |
| }, | |
| { | |
| "dataPath": "params_shard_128.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e43b94e163d4b8c13f382b63140f61cc" | |
| }, | |
| { | |
| "dataPath": "params_shard_129.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.31.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f7fcb57d7e9b676863c6de99e4858c56" | |
| }, | |
| { | |
| "dataPath": "params_shard_130.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.32.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "95751c5450372540847b46b60262b812" | |
| }, | |
| { | |
| "dataPath": "params_shard_131.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.32.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "49e938910df7eb4c977c63d7b365fc85" | |
| }, | |
| { | |
| "dataPath": "params_shard_132.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.32.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f7d02de9c87f86fbaf7906f7b2f0848c" | |
| }, | |
| { | |
| "dataPath": "params_shard_133.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.32.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bbf92b3411bf6e34262e4f82b11a13c2" | |
| }, | |
| { | |
| "dataPath": "params_shard_134.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4c29e4cba3e8284b5730b893f02a2f05" | |
| }, | |
| { | |
| "dataPath": "params_shard_135.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b6a2d9a756b6a5d69417ebd0582aac8f" | |
| }, | |
| { | |
| "dataPath": "params_shard_136.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3859738b90bc865b06285f7e27378f0d" | |
| }, | |
| { | |
| "dataPath": "params_shard_137.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.33.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "24a571adf5b48ff82f318ddd1ce53ee9" | |
| }, | |
| { | |
| "dataPath": "params_shard_138.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.34.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "850112c050c28e13b09bf08fbd497326" | |
| }, | |
| { | |
| "dataPath": "params_shard_139.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.34.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f74ecb3994296a5cee3ff284014b97af" | |
| }, | |
| { | |
| "dataPath": "params_shard_140.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.34.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "038494d41a1885018f364f8fa35c6e45" | |
| }, | |
| { | |
| "dataPath": "params_shard_141.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.34.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "127aac66fd30da5156ac9e2432a094e9" | |
| }, | |
| { | |
| "dataPath": "params_shard_142.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.mlp.down_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 12288 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3e7cb16dc5356a27e20935863249c7ea" | |
| }, | |
| { | |
| "dataPath": "params_shard_143.bin", | |
| "format": "raw-shard", | |
| "nbytes": 201326592, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 24576, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 201326592, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7333c27b115bec3cf63bcdab2ae11c48" | |
| }, | |
| { | |
| "dataPath": "params_shard_144.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.self_attn.c_attn.weight", | |
| "shape": [ | |
| 6144, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "da4d1431a7a75f9bc33fca97c76468be" | |
| }, | |
| { | |
| "dataPath": "params_shard_145.bin", | |
| "format": "raw-shard", | |
| "nbytes": 33554432, | |
| "records": [ | |
| { | |
| "name": "model.layers.35.self_attn.o_proj.weight", | |
| "shape": [ | |
| 4096, | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 33554432, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "12fea0968a834a4b8ad542846e8bd6a9" | |
| }, | |
| { | |
| "dataPath": "params_shard_146.bin", | |
| "format": "raw-shard", | |
| "nbytes": 616448, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 8192 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 16384 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 16640 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 16896 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 25088 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 33280 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 33536 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 33792 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 41984 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 50176 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 50432 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 50688 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 58880 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 67072 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 67328 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 67584 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 75776 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 83968 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 84224 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 84480 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 92672 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 100864 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 101120 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 101376 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 109568 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 117760 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 118016 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 118272 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 126464 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 134656 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 134912 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 135168 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 143360 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 151552 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 151808 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 152064 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 160256 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 168448 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 168704 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 168960 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 177152 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 185344 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 185600 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 185856 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 194048 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 202240 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 202496 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 202752 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 210944 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 219136 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 219392 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 219648 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 227840 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 236032 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 236288 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 236544 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 236800 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 237056 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 245248 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 253440 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 253696 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 253952 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 262144 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 270336 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 270592 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 270848 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 279040 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 287232 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 287488 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 287744 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 295936 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 304128 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 312320 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 320512 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 320768 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 321024 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 329216 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 337408 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 337664 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 337920 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 346112 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 354304 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 354560 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 354816 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 363008 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 371200 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 371456 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 371712 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 379904 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 388096 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 388352 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 388608 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 396800 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 404992 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 405248 | |
| }, | |
| { | |
| "name": "model.layers.24.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 405504 | |
| }, | |
| { | |
| "name": "model.layers.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 413696 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 421888 | |
| }, | |
| { | |
| "name": "model.layers.24.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 422144 | |
| }, | |
| { | |
| "name": "model.layers.25.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 422400 | |
| }, | |
| { | |
| "name": "model.layers.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 430592 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 438784 | |
| }, | |
| { | |
| "name": "model.layers.25.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 439040 | |
| }, | |
| { | |
| "name": "model.layers.26.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 439296 | |
| }, | |
| { | |
| "name": "model.layers.26.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 447488 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 455680 | |
| }, | |
| { | |
| "name": "model.layers.26.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 455936 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 456192 | |
| }, | |
| { | |
| "name": "model.layers.27.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 456448 | |
| }, | |
| { | |
| "name": "model.layers.27.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 456704 | |
| }, | |
| { | |
| "name": "model.layers.27.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 464896 | |
| }, | |
| { | |
| "name": "model.layers.28.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 473088 | |
| }, | |
| { | |
| "name": "model.layers.28.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 481280 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 489472 | |
| }, | |
| { | |
| "name": "model.layers.28.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 489728 | |
| }, | |
| { | |
| "name": "model.layers.29.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 489984 | |
| }, | |
| { | |
| "name": "model.layers.29.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 498176 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 506368 | |
| }, | |
| { | |
| "name": "model.layers.29.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 506624 | |
| }, | |
| { | |
| "name": "model.layers.30.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 506880 | |
| }, | |
| { | |
| "name": "model.layers.30.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 515072 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 523264 | |
| }, | |
| { | |
| "name": "model.layers.30.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 523520 | |
| }, | |
| { | |
| "name": "model.layers.31.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 523776 | |
| }, | |
| { | |
| "name": "model.layers.31.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 531968 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 540160 | |
| }, | |
| { | |
| "name": "model.layers.31.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 540416 | |
| }, | |
| { | |
| "name": "model.layers.32.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 540672 | |
| }, | |
| { | |
| "name": "model.layers.32.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 548864 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 557056 | |
| }, | |
| { | |
| "name": "model.layers.32.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 557312 | |
| }, | |
| { | |
| "name": "model.layers.33.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 557568 | |
| }, | |
| { | |
| "name": "model.layers.33.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 565760 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 573952 | |
| }, | |
| { | |
| "name": "model.layers.33.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 574208 | |
| }, | |
| { | |
| "name": "model.layers.34.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 574464 | |
| }, | |
| { | |
| "name": "model.layers.34.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 582656 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 590848 | |
| }, | |
| { | |
| "name": "model.layers.34.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 591104 | |
| }, | |
| { | |
| "name": "model.layers.35.input_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 591360 | |
| }, | |
| { | |
| "name": "model.layers.35.post_attention_layernorm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 599552 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.k_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 607744 | |
| }, | |
| { | |
| "name": "model.layers.35.self_attn.q_norm.weight", | |
| "shape": [ | |
| 128 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 256, | |
| "byteOffset": 608000 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 4096 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8192, | |
| "byteOffset": 608256 | |
| } | |
| ], | |
| "md5sum": "cb1f4781d2ad2cb6ac50869077a212a6" | |
| } | |
| ] | |
| } |