{ "metadata": { "ParamSize": 33, "ParamBytes": 4282474496.0, "BitsPerParam": 16.0 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 1050673152, "records": [ { "name": "model.embed_tokens.weight", "shape": [ 128256, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1050673152, "byteOffset": 0 } ], "md5sum": "4f3abf3ebad1ecc8df2b2dfa35684d23" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "2b1b601e66a7b1b3d54b504005c82901" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.0.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "98f7bbcff1ef0eb6f6e77da193904eb5" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "244c3c1c73c1908144941da5eab46e6a" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.0.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "96fafa4addcbcf0632f6904134ca1b96" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "9c53b3a8ed363982122521ce781019f1" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.1.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "e89b7adc3d3ab3b3c5decceff7885fe6" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "2d3df5397ba57e0d76fbc4f9155cf65d" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.1.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "dcb3e25a81ba2a2ab5c6bae6600d1c95" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "378c7562979c4f8f768008c7edee3201" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.2.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "4d60721effacf52c49858816e5716d50" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "30139e818977be3d9c46e601c1bd6bcc" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.2.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "49d7ce0c32eace66487dbc599c272a72" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "01b34a7854620a3204015b720d8f959b" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.3.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "700677f7236e16c439efdb0c6fdafa8c" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "c151babcf27fa9765c61ddc773401f10" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.3.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "1fe2fb297b0021d92de0c5a2b60e960d" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.weight", "shape": [ 6144, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "77131a9c3f35f68419e0c721fccdc7b3" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33554432, "records": [ { "name": "model.layers.4.self_attn.o_proj.weight", "shape": [ 4096, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 33554432, "byteOffset": 0 } ], "md5sum": "5930fa703a8b1cbdd87a991d9128f701" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 234881024, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.weight", "shape": [ 28672, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 234881024, "byteOffset": 0 } ], "md5sum": "114302421fd094b771e25ed747846278" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 117440512, "records": [ { "name": "model.layers.4.mlp.down_proj.weight", "shape": [ 4096, 14336 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 117440512, "byteOffset": 0 } ], "md5sum": "b1025330c1b720912754167b06ef2009" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 1050673152, "records": [ { "name": "lm_head.weight", "shape": [ 128256, 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1050673152, "byteOffset": 0 } ], "md5sum": "1753899765f1afa12fdc2c9666669644" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 90112, "records": [ { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8192 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 16384 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24576 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32768 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 40960 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 49152 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 57344 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 65536 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 73728 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 81920 } ], "md5sum": "2e9bfe425272805c6418043474d53ef5" } ] }