{ "metadata": { "ParamSize": 31, "ParamBytes": 4044459008.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 1089994752, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 152064, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1089994752, "byteOffset": 0 } ], "md5sum": "04271b91cafad82f630343dcc1156d75" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 3584, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "23278f4c2c2bd26e27c57bf98ad4ef8c" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 271581184, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 37888, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 271581184, "byteOffset": 0 } ], "md5sum": "eab8149d005afce177602e3a0502e2d5" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 135790592, "records": [ { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 3584, 18944 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 135790592, "byteOffset": 0 } ], "md5sum": "d8c5636ba8c54a1bf9a9be52028edd24" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 33030144, "records": [ { "name": "model.layers.1.self_attn.c_attn.weight", "shape": [ 4608, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33030144, "byteOffset": 0 } ], "md5sum": "c03154c2e7e28390bd1554a72a582034" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 3584, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "d46398b81504bd2d82830108afdd8407" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 271581184, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 37888, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 271581184, "byteOffset": 0 } ], "md5sum": "92a7bea5fcddf575091c43b1c4df714c" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 135790592, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 3584, 18944 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 135790592, "byteOffset": 0 } ], "md5sum": "ccb811f73867d1f386520f524f2c01a2" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33030144, "records": [ { "name": "model.layers.2.self_attn.c_attn.weight", "shape": [ 4608, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33030144, "byteOffset": 0 } ], "md5sum": "8af6d905b41911171901c0c9b1309afb" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 3584, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "126e17f7b67d299092e34621d3d01ba5" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 271581184, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 37888, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 271581184, "byteOffset": 0 } ], "md5sum": "56b5611e7e548cbe8da292871a122b53" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 135790592, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 3584, 18944 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 135790592, "byteOffset": 0 } ], "md5sum": "dd79708597c0102a78c1c7487114aafe" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 33030144, "records": [ { "name": "model.layers.3.self_attn.c_attn.weight", "shape": [ 4608, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33030144, "byteOffset": 0 } ], "md5sum": "10c68f4a89d8c9e5ac3fd00b5ce2ee47" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25690112, "records": [ { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 3584, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 25690112, "byteOffset": 0 } ], "md5sum": "e655468aacdcefbc5172993aea2634e2" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 271581184, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 37888, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 271581184, "byteOffset": 0 } ], "md5sum": "ce9430ea30508f4c11646d9f6987c7d5" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 135790592, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 3584, 18944 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 135790592, "byteOffset": 0 } ], "md5sum": "8463225b5d39d8aa6befc7e394ff9a80" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 1089994752, "records": [ { "name": "lm_head.weight", "shape": [ 152064, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1089994752, "byteOffset": 0 } ], "md5sum": "edc0c39312d7ac18516c511b41a46f02" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 33131520, "records": [ { "name": "model.layers.0.self_attn.c_attn.weight", "shape": [ 4608, 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33030144, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 33030144 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33039360 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33046528 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 33053696 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33062912 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33070080 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 33077248 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33086464 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33093632 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9216, "byteOffset": 33100800 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33110016 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33117184 }, { "name": "model.norm.weight", "shape": [ 3584 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7168, "byteOffset": 33124352 } ], "md5sum": "70fbdf29d3964389bcae6e3d22e00b4c" } ] }