{ "metadata": { "ParamSize": 45, "ParamBytes": 710221824.0, "BitsPerParam": 4.500335784941911 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 113246208, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 55296, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 113246208, "byteOffset": 0 } ], "md5sum": "8a6e3d99368ecc20bfedb66a4753a489" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "6dc6b5a86964a1b8eaf979f2bdb65c5f" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f23c578d5279105a2475431b364d6082" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "de3af25993f69eee3d38d24398f34933" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32374784, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 55296, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 14155776 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17301504 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25690112 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26738688 } ], "md5sum": "4bbe7d5de8b78ecaca0e56086a595d2b" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 31145984, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2818048 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2826240 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 2834432 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 28000256 } ], "md5sum": "f188574cefeead2adf6866163c151917" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f419bbcd8f931798727fd5963f7b76a9" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "1ed071ab5bc7d7ed093e56bdcfc0dfc1" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "64517f2b3f4c35296dd9711cb6dd8748" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f3449ee6e8be73f2f04a55eb1354eed7" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 30490624, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 9437184 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 15073280 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 17891328 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 17899520 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 17907712 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 21053440 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 29442048 } ], "md5sum": "5b17842481ec0700776b00984d62fdd5" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "81dda134f78fe8bc32eb9333ffb489dd" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31014912, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 5636096 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 28180480 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 30998528 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 31006720 } ], "md5sum": "59366ee4fb0104a9d93e7a45c7a1a27a" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "ccb83f6c6dac4773793fdc5c474cc8c2" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "88a2bbad50d90a1e27ba7d1490d75aee" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 113246208, "records": [ { "name": "lm_head.q_weight", "shape": [ 55296, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 113246208, "byteOffset": 0 } ], "md5sum": "576ee2120b5bcefc80df4416726393ce" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 21061632, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 3145728 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 11534336 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 12582912 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 18219008 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21037056 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21053440 } ], "md5sum": "51bd241eece6fa67f1a4bd0dde4d5fff" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 14155776, "records": [ { "name": "lm_head.q_scale", "shape": [ 55296, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 14155776, "byteOffset": 0 } ], "md5sum": "dc48e203ccd2de292325004b14806dd3" } ] }