{ "metadata": { "ParamSize": 149, "ParamBytes": 652148736.0, "BitsPerParam": 41.92540933525066 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 28360704, "records": [ { "name": "transformer.h.0.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 0 }, { "name": "transformer.h.0.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 9216 }, { "name": "transformer.h.0.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7087104 }, { "name": "transformer.h.0.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7090176 }, { "name": "transformer.h.0.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.0.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9452544 }, { "name": "transformer.h.0.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9455616 }, { "name": "transformer.h.0.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9458688 }, { "name": "transformer.h.0.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9461760 }, { "name": "transformer.h.0.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9474048 }, { "name": "transformer.h.0.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18911232 }, { "name": "transformer.h.0.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18914304 }, { "name": "transformer.h.1.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28351488 } ], "md5sum": "592c5422821d96329c926f26df27faba" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.1.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.1.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.1.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.1.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.1.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.1.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.1.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.1.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.1.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.1.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.1.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.10.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "1239331c367550f8941ad73750c295d9" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.10.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.10.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.10.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.10.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.10.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.10.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.10.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.10.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.10.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.10.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.10.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.11.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "4f7d520002aeef8fd6f9a6f6d69a6990" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.11.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.11.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.11.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.11.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.11.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.11.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.11.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.11.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.11.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.11.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.11.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.2.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "3e441198374118c8bf6078c63292c2fc" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.2.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.2.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.2.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.2.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.2.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.2.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.2.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.2.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.2.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.2.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.2.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.3.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "07ddc8f8c1965fc3405057ab4ce8500f" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.3.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.3.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.3.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.3.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.3.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.3.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.3.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.3.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.3.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.3.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.3.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.4.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "7c210b48993fd601ec72181de2999b0d" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.4.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.4.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.4.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.4.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.4.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.4.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.4.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.4.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.4.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.4.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.4.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.5.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "2bd195357ec8d83a65b2a0c3bb41792f" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.5.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.5.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.5.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.5.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.5.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.5.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.5.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.5.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.5.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.5.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.5.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.6.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "94998ebd22456219b268fd4dd485ea54" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.6.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.6.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.6.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.6.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.6.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.6.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.6.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.6.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.6.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.6.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.6.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.7.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "7d3bb07ca75708ffde6fcc25b83deba9" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.7.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.7.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.7.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.7.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.7.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.7.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.7.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.7.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.7.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.7.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.7.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.8.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "2c81ab68fa79ef5d6b775704f3c00d0f" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28351488, "records": [ { "name": "transformer.h.8.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.8.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.8.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.8.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.8.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.8.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.8.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.8.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.8.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.8.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.8.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.h.9.attn.c_attn.bias", "shape": [ 2304 ], "dtype": "float32", "format": "raw", "nbytes": 9216, "byteOffset": 28342272 } ], "md5sum": "1ca6549012aa9317f2fcd8c3fccadada" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 154389504, "records": [ { "name": "lm_head.weight", "shape": [ 50257, 768 ], "dtype": "float32", "format": "raw", "nbytes": 154389504, "byteOffset": 0 } ], "md5sum": "4d4b2d98c89080badae51e93d79da2fe" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 154389504, "records": [ { "name": "transformer.wte.weight", "shape": [ 50257, 768 ], "dtype": "float32", "format": "raw", "nbytes": 154389504, "byteOffset": 0 } ], "md5sum": "4d4b2d98c89080badae51e93d79da2fe" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 31494144, "records": [ { "name": "transformer.h.9.attn.c_attn.weight", "shape": [ 2304, 768 ], "dtype": "float32", "format": "raw", "nbytes": 7077888, "byteOffset": 0 }, { "name": "transformer.h.9.attn.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 7077888 }, { "name": "transformer.h.9.attn.c_proj.weight", "shape": [ 768, 768 ], "dtype": "float32", "format": "raw", "nbytes": 2359296, "byteOffset": 7080960 }, { "name": "transformer.h.9.ln_1.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9440256 }, { "name": "transformer.h.9.ln_1.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9443328 }, { "name": "transformer.h.9.ln_2.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9446400 }, { "name": "transformer.h.9.ln_2.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 9449472 }, { "name": "transformer.h.9.mlp.c_fc.bias", "shape": [ 3072 ], "dtype": "float32", "format": "raw", "nbytes": 12288, "byteOffset": 9452544 }, { "name": "transformer.h.9.mlp.c_fc.weight", "shape": [ 3072, 768 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 9464832 }, { "name": "transformer.h.9.mlp.c_proj.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 18902016 }, { "name": "transformer.h.9.mlp.c_proj.weight", "shape": [ 768, 3072 ], "dtype": "float32", "format": "raw", "nbytes": 9437184, "byteOffset": 18905088 }, { "name": "transformer.ln_f.bias", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 28342272 }, { "name": "transformer.ln_f.weight", "shape": [ 768 ], "dtype": "float32", "format": "raw", "nbytes": 3072, "byteOffset": 28345344 }, { "name": "transformer.wpe.weight", "shape": [ 1024, 768 ], "dtype": "float32", "format": "raw", "nbytes": 3145728, "byteOffset": 28348416 } ], "md5sum": "bb8071bd499a922c01c5b8d298057aaf" } ] }