{ "metadata": { "ParamSize": 149, "ParamBytes": 681461760.0, "BitsPerParam": 32.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 28385280, "records": [ { "name": "transformer.h.0.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 0 }, { "name": "transformer.h.1.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 3072 }, { "name": "transformer.h.2.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 6144 }, { "name": "transformer.h.3.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9216 }, { "name": "transformer.h.4.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 12288 }, { "name": "transformer.h.5.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 15360 }, { "name": "transformer.h.6.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18432 }, { "name": "transformer.h.7.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 21504 }, { "name": "transformer.h.8.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 24576 }, { "name": "transformer.h.9.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 27648 }, { "name": "transformer.h.10.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 30720 }, { "name": "transformer.h.11.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 33792 }, { "name": "transformer.h.0.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 36864 }, { "name": "transformer.h.1.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 39936 }, { "name": "transformer.h.2.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 43008 }, { "name": "transformer.h.3.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 46080 }, { "name": "transformer.h.4.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 49152 }, { "name": "transformer.h.5.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 52224 }, { "name": "transformer.h.6.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 55296 }, { "name": "transformer.h.7.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 58368 }, { "name": "transformer.h.8.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 61440 }, { "name": "transformer.h.9.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 64512 }, { "name": "transformer.h.10.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 67584 }, { "name": "transformer.h.11.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 70656 }, { "name": "transformer.h.0.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 73728 }, { "name": "transformer.h.1.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 7151616 }, { "name": "transformer.h.2.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 14229504 }, { "name": "transformer.h.3.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 21307392 } ], "md5sum": "23007ed9914f6fb9f04ccbd14426d358" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "transformer.h.4.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.5.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 7077888 }, { "name": "transformer.h.6.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 14155776 }, { "name": "transformer.h.7.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 21233664 } ], "md5sum": "34800fa175402b89912639d507ac052b" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33140736, "records": [ { "name": "transformer.h.8.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.9.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 7077888 }, { "name": "transformer.h.10.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 14155776 }, { "name": "transformer.h.11.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 21233664 }, { "name": "transformer.h.0.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28311552 }, { "name": "transformer.h.1.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28320768 }, { "name": "transformer.h.2.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28329984 }, { "name": "transformer.h.3.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28339200 }, { "name": "transformer.h.4.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28348416 }, { "name": "transformer.h.5.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28357632 }, { "name": "transformer.h.6.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28366848 }, { "name": "transformer.h.7.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28376064 }, { "name": "transformer.h.8.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28385280 }, { "name": "transformer.h.9.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28394496 }, { "name": "transformer.h.10.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28403712 }, { "name": "transformer.h.11.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28412928 }, { "name": "transformer.h.0.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 28422144 }, { "name": "transformer.h.1.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 30781440 } ], "md5sum": "3bc3ef27da003e2e9a77760500ddaf55" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33140736, "records": [ { "name": "transformer.h.2.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 0 }, { "name": "transformer.h.3.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 2359296 }, { "name": "transformer.h.4.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 4718592 }, { "name": "transformer.h.5.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7077888 }, { "name": "transformer.h.6.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 9437184 }, { "name": "transformer.h.7.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 11796480 }, { "name": "transformer.h.8.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 14155776 }, { "name": "transformer.h.9.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 16515072 }, { "name": "transformer.h.10.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 18874368 }, { "name": "transformer.h.11.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 21233664 }, { "name": "transformer.h.0.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23592960 }, { "name": "transformer.h.1.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23596032 }, { "name": "transformer.h.2.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23599104 }, { "name": "transformer.h.3.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23602176 }, { "name": "transformer.h.4.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23605248 }, { "name": "transformer.h.5.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23608320 }, { "name": "transformer.h.6.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23611392 }, { "name": "transformer.h.7.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23614464 }, { "name": "transformer.h.8.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23617536 }, { "name": "transformer.h.9.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23620608 }, { "name": "transformer.h.10.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23623680 }, { "name": "transformer.h.11.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23626752 }, { "name": "transformer.h.0.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23629824 }, { "name": "transformer.h.1.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23632896 }, { "name": "transformer.h.2.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23635968 }, { "name": "transformer.h.3.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23639040 }, { "name": "transformer.h.4.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23642112 }, { "name": "transformer.h.5.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23645184 }, { "name": "transformer.h.6.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23648256 }, { "name": "transformer.h.7.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23651328 }, { "name": "transformer.h.8.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23654400 }, { "name": "transformer.h.9.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23657472 }, { "name": "transformer.h.10.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23660544 }, { "name": "transformer.h.11.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23663616 }, { "name": "transformer.h.0.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23666688 }, { "name": "transformer.h.1.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23669760 }, { "name": "transformer.h.2.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23672832 }, { "name": "transformer.h.3.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23675904 }, { "name": "transformer.h.4.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23678976 }, { "name": "transformer.h.5.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23682048 }, { "name": "transformer.h.6.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23685120 }, { "name": "transformer.h.7.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23688192 }, { "name": "transformer.h.8.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23691264 }, { "name": "transformer.h.9.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23694336 }, { "name": "transformer.h.10.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23697408 }, { "name": "transformer.h.11.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 23700480 }, { "name": "transformer.h.0.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 23703552 } ], "md5sum": "31854bcfd1e8696dece65b47518b87b3" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "transformer.h.1.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.2.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.3.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18874368 } ], "md5sum": "967b8189775a14280c96c82a222a2ff0" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "transformer.h.4.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.5.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.6.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18874368 } ], "md5sum": "f843773afbb5f2cec9ac7baa18fb2d1f" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "transformer.h.7.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.8.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.9.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18874368 } ], "md5sum": "e6dbc2df730448a99ee03e2b2b7db7ac" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28459008, "records": [ { "name": "transformer.h.10.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.11.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.0.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18874368 }, { "name": "transformer.h.1.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18886656 }, { "name": "transformer.h.2.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18898944 }, { "name": "transformer.h.3.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18911232 }, { "name": "transformer.h.4.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18923520 }, { "name": "transformer.h.5.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18935808 }, { "name": "transformer.h.6.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18948096 }, { "name": "transformer.h.7.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18960384 }, { "name": "transformer.h.8.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18972672 }, { "name": "transformer.h.9.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18984960 }, { "name": "transformer.h.10.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 18997248 }, { "name": "transformer.h.11.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 19009536 }, { "name": "transformer.h.0.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 19021824 } ], "md5sum": "7d5d8531365b099e637a8fa0019af00b" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "transformer.h.1.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.2.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.3.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18874368 } ], "md5sum": "605b25914c5d1814b6a87cd7ceb5bf4e" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "transformer.h.4.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.5.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.6.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18874368 } ], "md5sum": "ffa9ce5855d4cbe6455facb4399663f0" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28311552, "records": [ { "name": "transformer.h.7.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.8.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.9.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18874368 } ], "md5sum": "0f5a870c04c9c095e1cf30f23c9e579e" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 169046016, "records": [ { "name": "lm_head.weight", "shape": [ 55028, 768 ], "dtype": "float32", "format": "raw", "nbytes": 169046016, "byteOffset": 0 } ], "md5sum": "e913e1b035726d5af7b6bebe91ca5600" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 169046016, "records": [ { "name": "transformer.wte.weight", "shape": [ 55028, 768 ], "dtype": "float32", "format": "raw", "nbytes": 169046016, "byteOffset": 0 } ], "md5sum": "e913e1b035726d5af7b6bebe91ca5600" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 22063104, "records": [ { "name": "transformer.h.10.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 0 }, { "name": "transformer.h.11.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9437184 }, { "name": "transformer.h.0.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18874368 }, { "name": "transformer.h.1.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18877440 }, { "name": "transformer.h.2.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18880512 }, { "name": "transformer.h.3.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18883584 }, { "name": "transformer.h.4.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18886656 }, { "name": "transformer.h.5.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18889728 }, { "name": "transformer.h.6.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18892800 }, { "name": "transformer.h.7.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18895872 }, { "name": "transformer.h.8.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18898944 }, { "name": "transformer.h.9.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.10.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18905088 }, { "name": "transformer.h.11.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18908160 }, { "name": "transformer.ln_f.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18911232 }, { "name": "transformer.ln_f.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18914304 }, { "name": "transformer.wpe.weight", "shape": [ 1024, 768 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 18917376 } ], "md5sum": "9ec2e8bf42f82c144cfd2253047927c2" } ] }