| { | |
| "metadata": { | |
| "ParamSize": 195, | |
| "ParamBytes": 15284318208.0, | |
| "BitsPerParam": 32.0 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 197001216, | |
| "records": [ | |
| { | |
| "name": "lm_head.weight", | |
| "shape": [ | |
| 32064, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 197001216, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8a8527ae759bcdc00a5370e9bdd02c76" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.21.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "39ce8a2e4a490788bca2bfc5d29ee750" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.21.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "03f4b4e140f6e3cde52d17858050bb89" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.21.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "86ecdb6c5c1a97e9d51edf8b5e946e3f" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.22.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9fc268af4e189817bc39b59f0b6bb8df" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.22.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "20af9685a105f543d1449dd11a91a658" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.22.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "81bc3451a06f45721fb768efa16a5d8b" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.23.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e52f58291ec52bcbfd91289a9b4817d9" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.23.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3912e7359a2eeba8acea95227ebdc03d" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.23.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "21540be1a96a5db30ff7d71ae2235b4b" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.23.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3d219626734aa59eb53ad94d33237002" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.24.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f633f601fce10064c4154ed9475787cf" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.24.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6d94309d62d8021a10979aa9fcfbbb38" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.24.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3ebb359a0cbf798f056e97ec67b3d67f" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.24.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bbf11ec630172c6d7ff979229f7318c9" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.25.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0135998514fbdfe65646eaa07c630212" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.25.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0850bda34f008843454734cd630ea04b" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.25.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fc6d531354e744a8e20db9a9bbe3c034" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.25.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a9f5fd890dac355f69a12985116c1d37" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.26.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "67790ceaa4cfcd9ab0e50fd419e414aa" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.26.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a84d31402ab305f7336678f6817ff661" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.26.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0684649e34806a6cf1082eeb07bee280" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.26.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a9525db749fa6fd8b0376748075c6cd2" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.27.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e33f5caac041c2431f192b63c4b9408c" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.27.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f1ba713e5c6c8155bf882b2f98176989" | |
| }, | |
| { | |
| "dataPath": "params_shard_25.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.27.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "de2ee43ed5144c2018e7fe87e0e6da4c" | |
| }, | |
| { | |
| "dataPath": "params_shard_26.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.27.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "09ff61a11971424fb2cf026de4aaf3d4" | |
| }, | |
| { | |
| "dataPath": "params_shard_27.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.28.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9335ec84caa6194779f893e837220f22" | |
| }, | |
| { | |
| "dataPath": "params_shard_28.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.28.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "80ac0e06b34c933f0037b0bbcf342d56" | |
| }, | |
| { | |
| "dataPath": "params_shard_29.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.28.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b249533ee7a2c71e6924c03a3d7ba2f6" | |
| }, | |
| { | |
| "dataPath": "params_shard_30.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.28.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c21d89f6008d35fab4a801d13a33d6e4" | |
| }, | |
| { | |
| "dataPath": "params_shard_31.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.29.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2d5e1873b354bebd7d4eeb179c1a1b4d" | |
| }, | |
| { | |
| "dataPath": "params_shard_32.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.29.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "1177243cc7f2760f00708519e4155d35" | |
| }, | |
| { | |
| "dataPath": "params_shard_33.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.29.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "64b093c6f9b576cefb4990b687d4f772" | |
| }, | |
| { | |
| "dataPath": "params_shard_34.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.29.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e751b0b62f3ceb2ccb03ee511f9587c2" | |
| }, | |
| { | |
| "dataPath": "params_shard_35.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.30.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d7838c0b1385d43bc8f2885c53097909" | |
| }, | |
| { | |
| "dataPath": "params_shard_36.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.30.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a01af9bdc270e47d9d34e18327db163e" | |
| }, | |
| { | |
| "dataPath": "params_shard_37.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.30.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d6bb036fd12afb7a8858a002a992bad1" | |
| }, | |
| { | |
| "dataPath": "params_shard_38.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.30.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2343f4e48865a2f1ca34bbf90de8e94b" | |
| }, | |
| { | |
| "dataPath": "params_shard_39.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.31.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6e785ca50bc36f3b72b9a8b31028ed1e" | |
| }, | |
| { | |
| "dataPath": "params_shard_40.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.31.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3e327a6e59fa93169e51759323062ed9" | |
| }, | |
| { | |
| "dataPath": "params_shard_41.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.31.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8a63c0ee03d719f9cb254dba411fd1e8" | |
| }, | |
| { | |
| "dataPath": "params_shard_42.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.31.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7b38f9bd15bde50f3cb6e251136fd9db" | |
| }, | |
| { | |
| "dataPath": "params_shard_43.bin", | |
| "format": "raw-shard", | |
| "nbytes": 197001216, | |
| "records": [ | |
| { | |
| "name": "transformer.embd.weight", | |
| "shape": [ | |
| 32064, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 197001216, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "84c6884cb403f4ebda31b1f0cd11147a" | |
| }, | |
| { | |
| "dataPath": "params_shard_44.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.0.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "02b92c4745b3aaf3af93fd1bafd9743d" | |
| }, | |
| { | |
| "dataPath": "params_shard_45.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.0.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "86280eb53bbe305c285f46f2526100ad" | |
| }, | |
| { | |
| "dataPath": "params_shard_46.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.0.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eb01bfd227dd1a3c385214a9227281dd" | |
| }, | |
| { | |
| "dataPath": "params_shard_47.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.0.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "094fd9aa8012f6a4056172aaa70a101b" | |
| }, | |
| { | |
| "dataPath": "params_shard_48.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.1.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "abe419a8bf9403f417ee9cc43a113c55" | |
| }, | |
| { | |
| "dataPath": "params_shard_49.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.1.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c7afaee525bd5cfaf486452f7e9da793" | |
| }, | |
| { | |
| "dataPath": "params_shard_50.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.1.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "c347b6d66f9cb99f11948798f3e32bb8" | |
| }, | |
| { | |
| "dataPath": "params_shard_51.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.1.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6afba897bb7baa4709551c59c52876ce" | |
| }, | |
| { | |
| "dataPath": "params_shard_52.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.10.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4cb357d3089f1c8419c64a7005a0be07" | |
| }, | |
| { | |
| "dataPath": "params_shard_53.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.10.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "eecde8c7bf9dae9fab5aa7812a3975b6" | |
| }, | |
| { | |
| "dataPath": "params_shard_54.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.10.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "501c8d1a929ac5ac1011c905522bbda7" | |
| }, | |
| { | |
| "dataPath": "params_shard_55.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.10.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "fe5081bba79c96809eaae1afc8992e9e" | |
| }, | |
| { | |
| "dataPath": "params_shard_56.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.11.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f5a1ce37301174a70112f80e9c8dbbb7" | |
| }, | |
| { | |
| "dataPath": "params_shard_57.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.11.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4d3a19abf572380beaaa8a78efc9cf5d" | |
| }, | |
| { | |
| "dataPath": "params_shard_58.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.11.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3b01504584a6675190372b99af01ee98" | |
| }, | |
| { | |
| "dataPath": "params_shard_59.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.11.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7c740c32e36d7bfc74f2d17f213e20d8" | |
| }, | |
| { | |
| "dataPath": "params_shard_60.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.12.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cf21374f37f0f5b01227300165e0f00d" | |
| }, | |
| { | |
| "dataPath": "params_shard_61.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.12.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "77d931dea52d952938302e11133f036f" | |
| }, | |
| { | |
| "dataPath": "params_shard_62.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.12.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4f71f9a45066e5c31bf25920f385fade" | |
| }, | |
| { | |
| "dataPath": "params_shard_63.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.12.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ca8f20312bf63def4afdcb7a79fdd14d" | |
| }, | |
| { | |
| "dataPath": "params_shard_64.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.13.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6131d68864376b2c8ec2662f6ddf0bc0" | |
| }, | |
| { | |
| "dataPath": "params_shard_65.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.13.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6fcab4795d71777030d35b04e981bd84" | |
| }, | |
| { | |
| "dataPath": "params_shard_66.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.13.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "492bd73874abbd261857c438d648133f" | |
| }, | |
| { | |
| "dataPath": "params_shard_67.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.13.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "283334a66c1ff540246fba153053a597" | |
| }, | |
| { | |
| "dataPath": "params_shard_68.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.14.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "503c60140693e1afbb3a82547d40148d" | |
| }, | |
| { | |
| "dataPath": "params_shard_69.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.14.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "24ecece564d481776fa10c5c48cd2b70" | |
| }, | |
| { | |
| "dataPath": "params_shard_70.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.14.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e39da289196f5e34ce97e4e9986f7a9d" | |
| }, | |
| { | |
| "dataPath": "params_shard_71.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.14.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "92de49e96266dda68dbd0704fc1ad1be" | |
| }, | |
| { | |
| "dataPath": "params_shard_72.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.15.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "53a1741060fc2dd3880e583ad8ed5ff3" | |
| }, | |
| { | |
| "dataPath": "params_shard_73.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.15.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ae55bfff4acf64bc5510724e4a736ec2" | |
| }, | |
| { | |
| "dataPath": "params_shard_74.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.15.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b079984a257eb7027b702f2c302a327e" | |
| }, | |
| { | |
| "dataPath": "params_shard_75.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.15.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a42fec30c15b7d8c3143e427f7f5088d" | |
| }, | |
| { | |
| "dataPath": "params_shard_76.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.16.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "3a7cc1f8ba95fd79f3d39cb1ea9fd857" | |
| }, | |
| { | |
| "dataPath": "params_shard_77.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.16.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b543efe30a61c8a579238393f418f24e" | |
| }, | |
| { | |
| "dataPath": "params_shard_78.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.16.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ac879528cda01c226e18671a884ccc51" | |
| }, | |
| { | |
| "dataPath": "params_shard_79.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.16.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "54230a1092e83442dfc60f8147666e40" | |
| }, | |
| { | |
| "dataPath": "params_shard_80.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.17.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "42ca676f9700721ba2a727e7fefab474" | |
| }, | |
| { | |
| "dataPath": "params_shard_81.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.17.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "6ae3f5a92c013d331f2bdbaebe1a40c0" | |
| }, | |
| { | |
| "dataPath": "params_shard_82.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.17.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "50dbc5c1c0976e2c2550c7fe80494ba2" | |
| }, | |
| { | |
| "dataPath": "params_shard_83.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.17.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "40fa333f537be594d0c7155ae809ae72" | |
| }, | |
| { | |
| "dataPath": "params_shard_84.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.18.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "33ed1d79c5ed79b91fefe7a93a151591" | |
| }, | |
| { | |
| "dataPath": "params_shard_85.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.18.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e08e060ac5d2bbed0b616f526c72648b" | |
| }, | |
| { | |
| "dataPath": "params_shard_86.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.18.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bda375d67d4721444184265e052e4b8a" | |
| }, | |
| { | |
| "dataPath": "params_shard_87.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.18.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "65b78f9e7b415da84b813eeaa96925e8" | |
| }, | |
| { | |
| "dataPath": "params_shard_88.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.19.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "bbb3f20449185aeeda24d9013bc6863a" | |
| }, | |
| { | |
| "dataPath": "params_shard_89.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.19.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8dff98cf2786c4e9ffe5cad1f02096b5" | |
| }, | |
| { | |
| "dataPath": "params_shard_90.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.19.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "139e697397308bf1ab79b401e0cca01c" | |
| }, | |
| { | |
| "dataPath": "params_shard_91.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.19.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "296f344ae12e5353045a15bf5081e5d8" | |
| }, | |
| { | |
| "dataPath": "params_shard_92.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.2.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7ffb0493d4c8865d5148edb22758d82e" | |
| }, | |
| { | |
| "dataPath": "params_shard_93.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.2.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7db5b27076285e180c4e5ed9a3cfb073" | |
| }, | |
| { | |
| "dataPath": "params_shard_94.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.2.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "9140ee44ab8686ffd0822c3cb4a99118" | |
| }, | |
| { | |
| "dataPath": "params_shard_95.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.2.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "82d05bfb58c3ec91744f816974ac880b" | |
| }, | |
| { | |
| "dataPath": "params_shard_96.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.20.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "848f919e5885b54a27f01b22c983b7b3" | |
| }, | |
| { | |
| "dataPath": "params_shard_97.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.20.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "d6c89047eab5c16a04cfd150cf07771d" | |
| }, | |
| { | |
| "dataPath": "params_shard_98.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.20.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "cbce1f68501b9f9578c0c46723b38b3c" | |
| }, | |
| { | |
| "dataPath": "params_shard_99.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.20.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0ecb273044dd33be4f0788053243a8ec" | |
| }, | |
| { | |
| "dataPath": "params_shard_100.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.21.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "94729ba67a8406d881005fe9793f2ef3" | |
| }, | |
| { | |
| "dataPath": "params_shard_101.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.3.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "dbe24432fb08eb0d004c367770940948" | |
| }, | |
| { | |
| "dataPath": "params_shard_102.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.3.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "4da389e83a2b277f484d83d2271e1649" | |
| }, | |
| { | |
| "dataPath": "params_shard_103.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.3.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "228a8cd5ca560207101d289aeed446ad" | |
| }, | |
| { | |
| "dataPath": "params_shard_104.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.3.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "75bd9f51d3b5bd245bf0a303065e2fad" | |
| }, | |
| { | |
| "dataPath": "params_shard_105.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.4.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0b4d8c43b5b8acb264030debcc11e0aa" | |
| }, | |
| { | |
| "dataPath": "params_shard_106.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.4.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "062442d286d67f7dad47b25dd0353840" | |
| }, | |
| { | |
| "dataPath": "params_shard_107.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.4.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8d9b5c2bd356ff6452f12a390419a667" | |
| }, | |
| { | |
| "dataPath": "params_shard_108.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.4.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "857acd38f42e460ab84354837d9c5c4e" | |
| }, | |
| { | |
| "dataPath": "params_shard_109.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.5.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "ce7a87f8ab87c9ee70bb1407c6d57d7b" | |
| }, | |
| { | |
| "dataPath": "params_shard_110.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.5.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "5bbdf2e42447ae99406e1899b27e123a" | |
| }, | |
| { | |
| "dataPath": "params_shard_111.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.5.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0752a8d08356310cd14780594c90e733" | |
| }, | |
| { | |
| "dataPath": "params_shard_112.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.5.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "a374b9818c6df3d50f66f6f90231e9c4" | |
| }, | |
| { | |
| "dataPath": "params_shard_113.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.6.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2d1cd7ad263a87c5c2e030472ecc3096" | |
| }, | |
| { | |
| "dataPath": "params_shard_114.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.6.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "64c63c1b23069fe0b9056545df4ee45c" | |
| }, | |
| { | |
| "dataPath": "params_shard_115.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.6.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f59a92bcf73a26af9e3728d0f6aa950c" | |
| }, | |
| { | |
| "dataPath": "params_shard_116.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.6.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "f390225a386c0da05176330e5616ce60" | |
| }, | |
| { | |
| "dataPath": "params_shard_117.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.7.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "b23cee340a4655f767c362d6ae0c117e" | |
| }, | |
| { | |
| "dataPath": "params_shard_118.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.7.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0ade9275c2c206eaae23520ee2d26887" | |
| }, | |
| { | |
| "dataPath": "params_shard_119.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.7.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "37a92d7b3d3c46d280f466f81478c20a" | |
| }, | |
| { | |
| "dataPath": "params_shard_120.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.7.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "7dce9ae0789b4ae0c43ff8028d039616" | |
| }, | |
| { | |
| "dataPath": "params_shard_121.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.8.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "2cf4ce6ace2e3c3bcddd7f13ff9af25c" | |
| }, | |
| { | |
| "dataPath": "params_shard_122.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.8.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "0ac137c2de87f22305db0695f3873d1b" | |
| }, | |
| { | |
| "dataPath": "params_shard_123.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.8.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "61cc1161f3204656eb7b58770a2386d5" | |
| }, | |
| { | |
| "dataPath": "params_shard_124.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.8.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e37b4bd8e1b448aebcda99d211727ebf" | |
| }, | |
| { | |
| "dataPath": "params_shard_125.bin", | |
| "format": "raw-shard", | |
| "nbytes": 50331648, | |
| "records": [ | |
| { | |
| "name": "transformer.h.9.mlp.down_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 8192 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 50331648, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "e81078b0c55d124dcecb0a07c98b4baa" | |
| }, | |
| { | |
| "dataPath": "params_shard_126.bin", | |
| "format": "raw-shard", | |
| "nbytes": 100663296, | |
| "records": [ | |
| { | |
| "name": "transformer.h.9.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 16384, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 100663296, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "81a34bddc2c26a192bc399eae7c2cf55" | |
| }, | |
| { | |
| "dataPath": "params_shard_127.bin", | |
| "format": "raw-shard", | |
| "nbytes": 18874368, | |
| "records": [ | |
| { | |
| "name": "transformer.h.9.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "788433b682d2b1bee05511a415162793" | |
| }, | |
| { | |
| "dataPath": "params_shard_128.bin", | |
| "format": "raw-shard", | |
| "nbytes": 56623104, | |
| "records": [ | |
| { | |
| "name": "transformer.h.9.mixer.qkv_proj.weight", | |
| "shape": [ | |
| 9216, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 56623104, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "523382519338e40987f11b0dd41d9cde" | |
| }, | |
| { | |
| "dataPath": "params_shard_129.bin", | |
| "format": "raw-shard", | |
| "nbytes": 19273728, | |
| "records": [ | |
| { | |
| "name": "transformer.h.21.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "transformer.h.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 6144 | |
| }, | |
| { | |
| "name": "transformer.h.22.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 12288 | |
| }, | |
| { | |
| "name": "transformer.h.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18432 | |
| }, | |
| { | |
| "name": "transformer.h.22.mixer.out_proj.weight", | |
| "shape": [ | |
| 3072, | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 18874368, | |
| "byteOffset": 24576 | |
| }, | |
| { | |
| "name": "transformer.h.23.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18898944 | |
| }, | |
| { | |
| "name": "transformer.h.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18905088 | |
| }, | |
| { | |
| "name": "transformer.h.24.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18911232 | |
| }, | |
| { | |
| "name": "transformer.h.24.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18917376 | |
| }, | |
| { | |
| "name": "transformer.h.25.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18923520 | |
| }, | |
| { | |
| "name": "transformer.h.25.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18929664 | |
| }, | |
| { | |
| "name": "transformer.h.26.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18935808 | |
| }, | |
| { | |
| "name": "transformer.h.26.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18941952 | |
| }, | |
| { | |
| "name": "transformer.h.27.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18948096 | |
| }, | |
| { | |
| "name": "transformer.h.27.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18954240 | |
| }, | |
| { | |
| "name": "transformer.h.28.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18960384 | |
| }, | |
| { | |
| "name": "transformer.h.28.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18966528 | |
| }, | |
| { | |
| "name": "transformer.h.29.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18972672 | |
| }, | |
| { | |
| "name": "transformer.h.29.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18978816 | |
| }, | |
| { | |
| "name": "transformer.h.30.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18984960 | |
| }, | |
| { | |
| "name": "transformer.h.30.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18991104 | |
| }, | |
| { | |
| "name": "transformer.h.31.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 18997248 | |
| }, | |
| { | |
| "name": "transformer.h.31.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19003392 | |
| }, | |
| { | |
| "name": "transformer.norm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19009536 | |
| }, | |
| { | |
| "name": "transformer.h.0.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19015680 | |
| }, | |
| { | |
| "name": "transformer.h.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19021824 | |
| }, | |
| { | |
| "name": "transformer.h.1.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19027968 | |
| }, | |
| { | |
| "name": "transformer.h.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19034112 | |
| }, | |
| { | |
| "name": "transformer.h.10.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19040256 | |
| }, | |
| { | |
| "name": "transformer.h.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19046400 | |
| }, | |
| { | |
| "name": "transformer.h.11.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19052544 | |
| }, | |
| { | |
| "name": "transformer.h.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19058688 | |
| }, | |
| { | |
| "name": "transformer.h.12.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19064832 | |
| }, | |
| { | |
| "name": "transformer.h.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19070976 | |
| }, | |
| { | |
| "name": "transformer.h.13.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19077120 | |
| }, | |
| { | |
| "name": "transformer.h.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19083264 | |
| }, | |
| { | |
| "name": "transformer.h.14.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19089408 | |
| }, | |
| { | |
| "name": "transformer.h.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19095552 | |
| }, | |
| { | |
| "name": "transformer.h.15.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19101696 | |
| }, | |
| { | |
| "name": "transformer.h.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19107840 | |
| }, | |
| { | |
| "name": "transformer.h.16.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19113984 | |
| }, | |
| { | |
| "name": "transformer.h.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19120128 | |
| }, | |
| { | |
| "name": "transformer.h.17.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19126272 | |
| }, | |
| { | |
| "name": "transformer.h.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19132416 | |
| }, | |
| { | |
| "name": "transformer.h.18.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19138560 | |
| }, | |
| { | |
| "name": "transformer.h.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19144704 | |
| }, | |
| { | |
| "name": "transformer.h.19.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19150848 | |
| }, | |
| { | |
| "name": "transformer.h.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19156992 | |
| }, | |
| { | |
| "name": "transformer.h.2.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19163136 | |
| }, | |
| { | |
| "name": "transformer.h.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19169280 | |
| }, | |
| { | |
| "name": "transformer.h.20.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19175424 | |
| }, | |
| { | |
| "name": "transformer.h.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19181568 | |
| }, | |
| { | |
| "name": "transformer.h.3.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19187712 | |
| }, | |
| { | |
| "name": "transformer.h.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19193856 | |
| }, | |
| { | |
| "name": "transformer.h.4.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19200000 | |
| }, | |
| { | |
| "name": "transformer.h.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19206144 | |
| }, | |
| { | |
| "name": "transformer.h.5.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19212288 | |
| }, | |
| { | |
| "name": "transformer.h.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19218432 | |
| }, | |
| { | |
| "name": "transformer.h.6.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19224576 | |
| }, | |
| { | |
| "name": "transformer.h.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19230720 | |
| }, | |
| { | |
| "name": "transformer.h.7.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19236864 | |
| }, | |
| { | |
| "name": "transformer.h.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19243008 | |
| }, | |
| { | |
| "name": "transformer.h.8.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19249152 | |
| }, | |
| { | |
| "name": "transformer.h.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19255296 | |
| }, | |
| { | |
| "name": "transformer.h.9.ln.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19261440 | |
| }, | |
| { | |
| "name": "transformer.h.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 3072 | |
| ], | |
| "dtype": "float32", | |
| "format": "f32-to-bf16", | |
| "nbytes": 6144, | |
| "byteOffset": 19267584 | |
| } | |
| ], | |
| "md5sum": "878e8856cab2008d92f6ab8e4466f9f8" | |
| } | |
| ] | |
| } |