{ "metadata": { "ParamSize": 325, "ParamBytes": 7581630464.0, "BitsPerParam": 9.000908730069483 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 131137536, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131137536, "byteOffset": 0 } ], "md5sum": "fe3086b8229a80897d27f2ea7ca567d9" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 131137536, "records": [ { "name": "lm_head.q_weight", "shape": [ 32016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 131137536, "byteOffset": 0 } ], "md5sum": "06398e840681c13eb1d7f1eb8493f05d" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "9aefb88fd4c0c8c4c5794985a4bb574d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "d9d58309176f7dda2fb7ec36104ec108" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "c468d0c5daa3f51b58964422c0e44a90" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "00bc5846aedc45577f6221f013b83354" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c9dda3f4a9a8200f09ca0bd5219d815c" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 16777216, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 0 } ], "md5sum": "2a64484f2ecf13faecf7db382ce07790" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "83bcd547da8b41c3bb81a7eae6652e92" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 33275904, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 32016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8196096, "byteOffset": 0 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8196096 }, { "name": "lm_head.q_scale", "shape": [ 32016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8196096, "byteOffset": 8204288 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 16400384 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 16408576 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 19554304 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 20602880 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 20611072 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 26247168 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29065216 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 29073408 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 32219136 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 33267712 } ], "md5sum": "dc4313583216bf486b6511ee9de800b1" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "4f2cbfd754ca3d8df30c980bd0560ab4" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "2bea893c26872a4863a1ee9a0d8bcadc" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "090008ef52727ed24aae041e2682d98d" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "233426f2eb9ceb446c993d86b82b6ee7" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "0bba473d10beb666bd28b297f7c658a4" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "abe18293950ceb4e4bc722f8283f7161" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "8b1e94f7c9a23708aa623cf37bef4774" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "fd8a0beb2c9e8f8a6ed4e25dd6f3aa25" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "2ed8696f98d6ebbb0c07089d1155c200" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "8fc193d544dd5cf3e78e5514c558a9bd" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "3b6d6673ac87f459078659d6c2fa4c9a" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "115eb749fc09bc4f1cbb4ea08c70da50" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "5021ba4ae3b2fd893ebf8297643207f9" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "5e35434f88d28fd44b13b774f488cf01" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "bac477da94c37979e7144c5ceb51e90c" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "e88d1dbe4e6ae96f24ef464a1e90b910" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "1bec4d3b1c6f60ddd71325fb8e1ef483" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "e078bd0d36f118baa89246419e431e46" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "eb729ea19b4f6a0c98771c9bd679f01b" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "7920563d18a8652ce39f888ccca5242f" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "271895ba226965b2d8e654f10d5e4068" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "b1bac04416e2c1ea364ed30b1fd20a86" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "3164a71f20f175d45f47ca1b8ab8e553" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "95763cebf460d89dcb903c18d8b50801" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "e42c7e376d62f36c51f080d582c51ba2" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "403c23fcebb7838953da926721a2aaee" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "f6f8e32594488b6037f43404e38a96be" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "bdb065aa33c00782b0d1f8811a02d6ff" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "0eeb32a771e827d8727cb2222e2b5e40" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "998f60a1911dee88f9aecc08e4326415" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "7e53fccee5610b837cd631498a4d4e2b" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "5d0b7e58e03cbb843961adf4d9b396cd" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "7e1ed5da7f675ec173f91b7f62a6bceb" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "2872d7b7d8dd022ef832c6b8470bd044" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a90c693db14b75e376f9aeff7248f953" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "67b62f602a5206fb96e87061354e5576" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f5db162be2e35b78a606938b5a7678dc" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "6c45a7b7fa2970b09cb3ae470eb61f62" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "255b5445c86ebe1f531e7db73b568978" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "e18d307a53fc19335fb02ff787519825" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "8252d7e268c36c5ee044de8c1b3abd22" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "c011cb514da6b23cbb727f89b806a392" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "700934ff3b7478d99ca0c2b94bda54c7" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "652f2ad524b315a37b8054ef8529140e" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "91cb5d6e2e330f40c37a7a58ec258dfa" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "4efc78b9a07c4a7c09484b52264c43f4" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "57c08394a38b01ffe3bdc7f80f5f7fdb" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "4dcfe149c95ae22b8696777e61c0ea24" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "51de55d1099c66a610a8d9b6684c3751" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "655086871fc386f7b7868efaaccddf68" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "dd9a236b4e5c23e2ed07e730fe84dbbd" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "b8b63605feba7c02983da5a323c22442" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "c41ef6df32abb2b9155dc63f0df9c694" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "1eacdb5c5a53183e164f2e9bd7accaa9" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "559c077a80dbce81f2bc6411efe9bb4b" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "fdc4acd60d9fa9d6f1d4e55285be6166" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "c9274518b72285bb22ee5c852272a185" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "a19799ae886b88a713b89458ee365c28" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "8380334b342082da91a887042cb4cc6b" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "693e8443ec525d103b01a1cce9d57d18" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "65ab96932aefd8fddbe7a2149d0bff3d" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "859a7fe895b7c2755a1a5d9b2754ce3b" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "35100b099c142b7678c767b803a70940" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "c68649851919cd49a5aa89cef6f8ebee" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "0baebb62ad21a7dd5511b3fa1ec2683e" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "44c623b2c47d43ab2942d4f3dcf4003d" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "973403eb4efd1e6f44bc86c0bce58ebf" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "891f7f256d8c78d511d6d299f9bcd811" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "50f338605fdabf002331a21dc9686970" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "fea66eab0a6c1629f3c27422737cf643" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "a03cf47fb23a24c7f26c95684ea39b3f" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "6ee84180d8d93613ecc7a83cbe7ad232" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "ab8017bf78f696f4a379a8c343bb8cc6" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "66f759f80e91400e906ea7ab55c77635" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "24fb31066a88c9df1f94708c43c8fd17" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "8400b729a6aa9ebfe09b12d5442ce6ba" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "6ba2377eab62a849f5244fb27b362d6c" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "b23f34a5ff3301fd2d2c0a620301c8db" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "0ec570f60549c436254f1688599c0fa5" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "38b7176d636a1a771f7a43aaca791d82" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "26c4ea4e2f64f5aeafda51bdb277cf9e" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "3c8dc370850c15ac99bf80dc30071a91" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "c77a9c8389f42433d73525f4d78d8887" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "07e70b69aaf9708d60414eea6fdba5d2" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "d647942a71c42352d25c2448efe1f0d7" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "ffe56ee009e3e8753b65c4564667fbcb" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "0fffe673c0ae08ad5273ad71a20fc754" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "03c700338e22aac9d7b322b1d3f84746" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "35a411677d7ea9a643c1a775e5b47295" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "04da0c04849dccaabad2f3c7c84dc6f8" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "79f88e0720d423c34876c352056173dc" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "5da525999641debb6e4f8706fd1dcd36" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "eb4d87e62b9e871997e7a04ddd376a4c" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "532a34d663444cb2768322ddc36324b4" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "31c3ed10cc1631bb7ab1a2016f3f79c9" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "f789294bbe230be8189e2925d152bafb" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "898d0c57ed94e396961af9b6330921d0" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "47c8fd610ccd4028bfbe7ca77d8513ef" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "4a13e6f2f88f92434fcc46d63579e530" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "66d6d0705a3227da1d683013f698f57c" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "fbada81b406c6c324f7e6693f2260553" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "ba89b9f9c7e17806a81051ed08c2e491" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "5918f36f05eb84d76f3cbad702f1afa1" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "b22db06364d155f5617cd4d972b7d2b4" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "cfc1302fea978f10a1241a0ba502d6e7" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "788b2fe482f9e1506e660b72117f9e34" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "1b734713e9459e400ee5d8a5fc0fc441" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "9d5038d5e3e11d8357b3a5c242e9ab0b" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "257c99098714b36b2ce23bd02df5e1e5" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "a49b26273eea56f8fbab3d128b5c155e" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d9ae5077d5f878c7882b1fd1f62742c3" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "afb570d734f9d4de92b2a64001c4ef48" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "06cb179b70c57052e62e4dad5510eba5" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "81615672fdea70f0886ad6b00484edbe" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "3de86e08fe9105194b08927a6ab4e633" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "9c7f801d748050f50bbb1593bd3bae56" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "94b9d40b82b9e457695d0bcb69d1b9e8" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 50331648, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 12288, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 50331648, "byteOffset": 0 } ], "md5sum": "8c269c425d1d161062ae8256d2b60ec6" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 90177536, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 22016, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 90177536, "byteOffset": 0 } ], "md5sum": "d678303b3916163ff236ea1fb3bf5329" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 29442048, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 1024 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 16777216, "byteOffset": 11608064 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1048576, "byteOffset": 28385280 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8192, "byteOffset": 29433856 } ], "md5sum": "0f69e13db8e499e505a348176b533454" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 2752 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "010a4cc2f419e43de327462d484ac001" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 8454144, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "bfloat16", "format": "raw", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "bfloat16", "format": "raw", "nbytes": 2818048, "byteOffset": 5636096 } ], "md5sum": "143d48815e90e7a242ec169763beec60" } ] }