{ "metadata": { "ParamSize": 325, "ParamBytes": 3790741504.0, "BitsPerParam": 4.500454373872803 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "de1096636ad485a8c5c09110454c57dc" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 30744576, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 0 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8192000 }, { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 8200192 } ], "md5sum": "f8b07028a89715624014a1feb1db919e" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "8f31b773f77ed6f2b2b1f6efa4cd1a69" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e9711331d06f0b8f3a2b0decbfbc2ac5" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "93d8623aa173380dc2a8fb18417ff48a" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "ee7d0049b0e83683c98a61dfe0c57fe0" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "1e3ad0992f3782f3812e3bcf4fc67891" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "0174f279ea30edece144134f338ae0ab" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "632a8eefcf64b800b23a6f63d8eff091" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "edbfd11650e1559c82529c0cd5f3c6a2" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e3ae79d6bd4b4770bb5995e65dcb0fe2" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "449acfc7d7e76ae23e9c5b9205b4c078" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "1af48438885cd6c1fc6bbf76c339ac0b" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "69f7185a461844b057e5b39fc8374379" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "4faa2b89b2b76f5d641a0b07fc4b59ee" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "4682b33fb8be67bb8182214672ddad6e" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "5dd2171bd06bc7b1350f66ecbb4815cd" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8c459dd4d6118f5dd6817a7433357329" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "0ae623f95d05754b9fc26342586710d9" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "e98b170d328b10c630a54277b22ffcfc" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "977e51bb26eb58e4855d1b010cbade3e" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "12cf030ea6e3554b7551639dc6ec9fb0" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "faed6ce8c68f30040e764a41b4354899" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "e5b1f7d1b2b335377349813e39bbb040" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "fccb8f644ba2fadfcefc478cf4ac9492" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "96fe9e3d50dce48825233b858977cd58" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "e79baf1d0ad3cac962c0f35543c0f31c" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a5499f8c46fcb9250d398f57e268e043" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "a2249710dc2af27bcd9a3473ecf67b75" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 65536000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 65536000, "byteOffset": 0 } ], "md5sum": "f974e508a83683152dd8d0b5b745a0a2" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "69a025e2b1db365ac6233b53cdbebde5" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "a3fa50c3497a1b9ea9039db6cac1c7ae" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "39b56088867c0626b0dc17f2fc118147" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 29253632, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192000, "byteOffset": 9445376 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 17637376 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 17645568 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 20463616 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26099712 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 26107904 } ], "md5sum": "1a36f451d7f51770893d35d7e4803912" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "2fcb4eb2ce28c47b51cde13f97687033" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "e9d940ba64169c4a20099245d2b741a1" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ceea8924283a459e4a22546e7f88e7a4" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "448fe0a3e126ad96d74016aff08e0e43" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "bfd1c59d8b8762eb71bdcbf38e15d28a" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d6e7e2e7ecb6bebeefa8eecf70947222" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "e4fe53a8664e48a9a0b2688152842c91" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "1765fa9fd625ae69819d6ac4d7d2ebe2" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "f1895f944ad87e9728b25abb2f6c94e8" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "2ae1ba41ae5aa869afb9b57890e37184" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "1de06d78759029f201a0a13e66b03114" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "a2ced1ae74c15bddf7662d2483dc831c" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "84a3f41aca432dd5651e43ec5aa6d6a2" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "7fe128618a0fad14681e7632a86cd42c" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "0e72a1e1fb2fc2e5252f8afa56da655f" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "7b6ca0cb272a374603ece2b2c65d5b6c" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3ee0c67c18503b112119afa9655f6ce9" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "33d6b1f58a5665d7e3242aff9db47514" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "9413d2845653d88ca869554d6dd4515d" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "19926c97cb3ccb3fe8e17b6a881d3d60" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "5f768c1b813340c268cb1b5694e8889e" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "4bc1ff9b53983e12588e16a307136cf4" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "7914d46ab1a0be1d954a1f9a812330b5" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "025617bf137bf1f744f638a69ef5eb84" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "e0fec23bb9981d2432fe2c4206659422" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "559eef05a8545f78f1e5dcc1096dc64b" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "2998c328d4dfd0d010d97909ac2dc177" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "bfc9e121ea36cb386065d9aa1f7da5bf" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "aaba85c74766bfb37b5e97ffa8b877bb" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "118981e1b26ae3b7bc01cccd7767d5d1" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "e9d28ccf1ad59fd6c63dbf3fa4f08ad1" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "1efce38e0e8abfd053b8825f62b97794" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "9568bef8132ddcceb420c893bdca4db4" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f037570b706b5f8f275a48424e74f131" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "16546f1529206c09eeafc2d54c01dff2" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "1213ad90f665d5885bc270e82a9c156d" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "8317d5e75386e7e5c0193a3fce95ed91" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "08c19412307fd0bb0a739b3c7d56c732" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "d6bc92252d2362030d269d231f14fd21" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "bdafe526a555a519a270c7f76ff4e277" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a8f2de76adde641c3eeff214526c4c25" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "5e94fd7630aa9afdfc316dba0534b04a" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "d34de9550502e74ad53e9f583a6b4326" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "73b55633f68741b14b76d5bd92960543" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "d27bbdd264bef7af1f8fe3d65564b1e3" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "c161a047b706dbcafe0bf24a2c48476b" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "fa67b0527d7fe960566550d100db8f9e" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8ba0c925bf129c2de403301053d0f9fa" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "4fd0106c9246de54542f4b00820dbda8" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "1ce26a297f7aac3d9981b406cbe9dc55" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "076c3fe92cab4fb6e313a71aa929ddb3" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "ba9014b453495fe1636d42a9264eebd0" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "270eae27409c0d0aa16dc00079acfded" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "bc49f2f4f0a420a6610a5038e84e4edf" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "f1b958ee45a947939eb9c3aebf1bec39" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "3388e0da5b9823f58e0de0ef3b4b7057" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "74d8972753bfb4d3ab24d4005ade0fa2" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "3e1f9b33a39cca907af516bc89af1ab7" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "5fc906b03fd15ff4d40225458dfcc3f2" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "b5ffe359ed1d7e811ae2f8b566eb92d5" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "eb27bd909a324cde3837bea5dc80fb76" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "c0a6b986b5a0da7fa8ce08f85707b187" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "40a804ee8b63b0ffeaf800441c9f70b9" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "f25cdb7660b975ef299626862226be98" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "e6d8b8c5b7877c841a2ea536945d97ba" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "322386c573f8080bc520fed1cb2c956b" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "00183c92850e786ea2b912a0954e9294" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "15cba2764788f351de81ac5f9dad193e" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "a3c402dbec2d1dafabbbfa5c1eddfb1f" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "7dc35cc38cb8568376098ad7f1bfb111" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "8ec9ae8fae42232dcee2dc4a8d250dac" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "58b429e41047d0f6c130d89bc84b598f" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "edff072b648d0d47232a21de0edc553c" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "db0443c26f7d7d20ff259f8b36efb867" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "b0a289775b0c123271c7b315252af49d" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "3462f9f326b0644d91a33bb5b5611c23" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 32661504, "records": [ { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21045248 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21053440 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 23871488 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29507584 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 29515776 } ], "md5sum": "2d1e64c59011fe49ce984a7639d2c7d2" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "44917b01d824cf052409c819ae9a18c0" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "ed4a874599224759db86cbf0bb8c4e5f" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 25165824, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 12288, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 25165824, "byteOffset": 0 } ], "md5sum": "8f57c7ab7ca22dc43a4dc9a06b53be06" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 21045248, "records": [ { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 2818048 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8454144 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 12288, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3145728, "byteOffset": 8462336 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11608064 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 19996672 } ], "md5sum": "0887821b2d7c353f78146f23090ffc79" } ] }