{ "metadata": { "ParamSize": 405, "ParamBytes": 5859330048.0, "BitsPerParam": 3.6013013960781106 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 65568768, "records": [ { "name": "lm_head.q_weight", "shape": [ 32016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65568768, "byteOffset": 0 } ], "md5sum": "f76b13b96fa07224c4f42e1735e519a6" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "71823bac1cbd8918bec861133190c4f4" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "e342d665c49f602260dc4d914c9984b2" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "a6ef0e784280371d5e433f32e6da3ab1" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ac155cefd2c614d4754f77d0a0bfa39f" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 26333184, "records": [ { "name": "lm_head.q_scale", "shape": [ 32016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8196096, "byteOffset": 0 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8196096 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 8206336 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11749376 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11759616 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11769856 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15312896 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22390784 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22401024 } ], "md5sum": "50726a06d09f7314d2b37d0c0913f4e9" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "fc051e3f6771e2a03ee3afae9dd9756e" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "fc076766069970b478536908b12633fe" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "9b6eaa3ade885786006b4035f5cc6053" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "1be15205c915bbc1478833967ee66fd8" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "2711e150c22c527ff4cb7fd137825b07" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "0dd707db6c578c43869d438efd223400" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "fe56b08cc5bf73d0fdbdd3f3e9b93220" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "ffa90bb37aa4c1666b256a469914beb6" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "70fe1bfe1b0bf0221e34f913b2e3b50b" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "836b055ed30128bc8faa83624d39c35c" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "56887f82858cf52e3110a67e0916afc9" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "4898b665296c229563ac1b0d5a32b4ef" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "a65ba62c9c197b3e73d5ef251706c921" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "843544a6839f737a78f17b52ceea84bd" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "8adb22e8585a1dd5f046a493ab10919f" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "7b3c29dad08f6457a68dc68555d455eb" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "5e02bb10110ef1f9bb8dbffbcdbb652c" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "00a8f7b5848ba4b08f097ee39b99c727" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "85f7da2994732aaf75d6cded73c0ec66" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "6614ca9d8487b9cf0006a8fe9f1563f0" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "83684fd458012ec4adfc894121c2bd85" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "23a19bb6ac16411dd9eee4b4bd617046" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "02540563cd4fffded90a185e9612ee7c" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "bf5b67c3fdb94d4dc81ef75b8c9db7c4" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "8a96ad13ad039fd2924428e7e1523cb5" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "bfd59562e2705ca093bedab4d57d29e2" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e67aca8a01ca80dff3dfff5446071d02" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "2ff582f07c86ed10c8eb097179f61318" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "3a22286f111767bcb2647da246a43c43" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "f362c24c03030f5044890a6a32c89353" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "9d0e08efda5ad72fe62143c0c0006236" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "b7dec2f7c812c49341c8c73a37198e61" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 65568768, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65568768, "byteOffset": 0 } ], "md5sum": "8bf2351a0df3bee9f36f68824e53ff70" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "4d4e17819e7a2fa6074e6f05c9fb4c96" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "e0f688d8adb52ebde97f77d110da8017" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0b2421c949c8586455bbad8128ad3544" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 30644224, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8196096, "byteOffset": 11806720 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 20002816 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 20013056 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 23556096 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30633984 } ], "md5sum": "c30b3e4484e199e9ccd0995ea2b77bd3" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "4ae7e86de60dd721f98cd201159d64df" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "60a869e7e020bcdd6ee71641cd330ebb" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "46f644cfbc02c6f2814b2951b306a4dc" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 30302208, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 3932160 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 14417920 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15728640 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 15738880 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 19281920 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26359808 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 26370048 } ], "md5sum": "4d96024a755ff85863ffdbf2c438b55e" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "a068a592852643d2e51900a3a8f502d0" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "f8b85bd412dd4f3225e1b031e668af29" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "e3184a6c959405e4d3e5260efe853c42" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "c8c28e390e0c87f654ab1c82a2e7753a" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "14649572ef1afa9799528dcfb147bec1" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "2c1db53b529c242cabb4eb553a889f4f" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "d1f7f3c4b010f335545bfec7cd2513de" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "d340ded885b11df77223fa0a010be629" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "69b0e215a253b4ee2b67fe47e8f044ef" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "b855c892f0cda541e438183527b5c6ab" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "10302983c032f991b22bcb27702f09fd" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "060bbf67aca971dc08c5922447d3cb2d" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "9704555fe20a7597bdcfb5dc5fd62475" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "83573ad5d4d3faeed3e19865475ad259" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b8e5e623b9867cff215e9d938146eb23" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "bc89517219faec7d22192b19d49f6d80" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "6915a756bf84c91eb39b3cc89c2ea581" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "2d343bc5e47307a873ef579ec4b1d3df" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b49360b49bd747aaa263e321bd167208" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "d63797cb52bf3a365b57fa4694b57d93" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "64f50d92d4ad6dc89f7db595272f126c" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "e15278f9f6345d727752087cd443ce6f" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "b4779aac1a81e1a36d86b0f0d483c0bf" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "bd0a5c2d1dce1272ce988193db2de00b" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 30302208, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 11796480 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15728640 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 15738880 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 19281920 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26359808 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 26370048 } ], "md5sum": "4e0b7a7aee6f3577e858853a2df18937" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "2fa76a41c535c1b592aa61a88446bae3" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4d7e2be901f717fc394a843775c7a998" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "29d32af801a0d7193191e489e53bdced" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "caec69fffa77ae4e0e70187199fa83bf" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "5abe0fe506f01571b115755f31db42fc" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4219e981055983914b659e30f435585f" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0f195cf114524b7e05ea0dcf982a0f38" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "31c4d109caed5591aad94bea94f84f6a" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "75fb771d962736deab7fae78e053996b" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4161bb23d3ead0f3aa5dc02c7bca0186" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "af1552c82c62b70ec7f48af874b94c9a" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "8799e47cf11913f167a2892a24ca8e8a" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "fb2a948adfcef2236efc990b3718c9f3" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "b3d9a047d85e12f988396dc7a7e3be36" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "622f635762c9d96597ab4d16fed1041e" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "882791fd4c0956186ec859d735200a54" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "38214a539a9860a0e5ec0adac130dcf3" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "3d866ae5f1374b40a8323e5e6b9256e4" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "57884c6d9fee2689aa193d9798262ced" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "ee387daec424d58521c6691222479bba" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "d07e62335e99ce566b75bd2ab1ba589e" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "f0cd38cd44931649b1b85da81d4921a8" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "cec0645a01bb579d1adfa55a0398f95a" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "d53544af6e3515a080d9abbd109253ba" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "c77635b963297f9c825d03d395041930" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "f09fabf4f0323d02c365f1ba0b4b125a" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "3ba2acc051a891179ac3b34757f1cd9f" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "3c3ee2a7a8fe9106b2c29cc8919ba0d9" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "834b4c0a7fb9094dfd94cb9a3e882573" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "b4a5144f71ad0679d039b301578bc70a" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 32923648, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 22437888 } ], "md5sum": "8382806ffe5cf577f245521cd248b9aa" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "9b24bf6789fe177b09e79fdf860b482d" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33208320, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 1310720 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 1320960 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 29665280 } ], "md5sum": "c3b60d200457f9cbe3fc9117fab59db6" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "bda0abb86af38f799bb5b63da19a8760" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "2a506d1fec3fd569d9d9df3ed3d971b6" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "ff54492405237ea4e8fbd97c956d592a" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "437da77a8f05521b5778d0d8e571a9d5" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 33458176, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 7077888 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 7088128 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 11020288 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 21506048 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22816768 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 22827008 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 26370048 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 33447936 } ], "md5sum": "ceae3a9b15636d613118c55e790fadbe" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "5e23b13c7ef872dc402a48189b0552fa" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "524f73733a4f3e43b0537baa94ec1dfe" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "35cae1546fdd7104ff85c276947b9db7" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 30302208, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 3932160 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 14417920 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 15728640 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 15738880 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 19281920 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26359808 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 26370048 } ], "md5sum": "42a58c62a101e4ab84c9e4fcc07aa4e1" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "1dc0168d428ff70217abf9f2c8c66f21" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "dd9e599ced0fa903dadfaf83fefa0c16" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "a385df3177f284fc827874e0d2563f96" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "88972a92946dccae0aad2a7048cda4b0" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "042a458b71f6b2c6014021f3d3094b95" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "2ab0342914359d30765693e8924940cd" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "2222215a6ee92cd5221cb0a631c52789" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "dedc127b69e219d8f8a4373de2eaa8a5" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "9f35c1823e4f6fe9ee800bf209c68d6f" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "9a61edaa121ce28b56afa06574cc1134" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "015d33e403bdd6025910ced794461278" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "9301a1b18152e1d6ce593858885e352a" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "14a49f84cd9e091ceeeb7c362cfde471" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "ea7c9dc02551eec238e3e983c39010f3" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "ca147f43b31528ccdae0311a7e6be9a5" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "4df6808a05282458380c609111c38049" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "8caf9bdde9bac0f4b4948757b8799e8f" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "9fbe3dd642f7426a0b73b49388073ad5" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "629e4445a312cd0fe49ed0cedb02eb2f" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "830351aa55c7318ee9943098440d0a24" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "fa5818a23ecf302de47d3a18f5acf2e2" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "356ab27a52c2024500a182e3d14d0714" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "b1f39cbc1b94ea201836c808f18e7ddd" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "95d6d2519959e373cf62b5f9fa8d6c5e" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "5c599d47e76aba605434df0702b8149d" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "9abcb808d4fff255dbad480f3df1a2be" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "7b00c61bb18e11fa2a4309352ea9655a" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "6682e718d912d0a7f51fad1f79edc748" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "3e85f89a52ea895548afb2bfe8c8aea6" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "4f3944a4986e728547960c3a29d129ae" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "0e18b0c0beece60a9134ec78ec077136" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "bb0359465dfa9a49bbe87a3b51f855e2" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "beb46c7dd3bc2f4681937846bb6f9ad6" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "ced406e982a30272fcec1f74f6f5a0a0" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "74befca77e6a1c8b813a6fed5e006121" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "982008b3d3a6f7c6c18bab0559e38e2f" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "7c164fdab803ce578bc8d3bfd2646191" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "44b91274f0ecf448eac265dabb5d1897" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "5c3856d67e21aa6b860368de17875460" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "82c232bd94ea8065d28429e5ec81fcfb" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 28344320, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 1384 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 28344320, "byteOffset": 0 } ], "md5sum": "59b0d106b13f37798b0398fc27e4d895" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "93d5b7a9a00d256d480995125a894215" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "779519df43766c47db3523b096243f50" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 26370048, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 11796480 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 346 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3543040, "byteOffset": 11806720 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 15349760 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 22427648 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 22437888 } ], "md5sum": "e0647fa46c27ba3f667aa34a3ba49909" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 56623104, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 27648, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 56623104, "byteOffset": 0 } ], "md5sum": "72eb010b8bbfc19f05e5c4376ec30a11" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 31457280, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 15360, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 31457280, "byteOffset": 0 } ], "md5sum": "89f640ff5b640343e7c8a1f13eb471ee" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 33292288, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 27648, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 7077888, "byteOffset": 11796480 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 15360, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3932160, "byteOffset": 18874368 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 22806528 } ], "md5sum": "3ed6e9e9a7fa607b60f1d0e0c29ef961" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 1310720, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 0 } ], "md5sum": "b8e48a4810d816ebfcbf5461b80611be" } ] }