{ "metadata": { "ParamSize": 325, "ParamBytes": 3476365312.0, "BitsPerParam": 4.500495468534268 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 160694272, "records": [ { "name": "lm_head.q_weight", "shape": [ 78464, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 160694272, "byteOffset": 0 } ], "md5sum": "7ad1c710cc6371ec67a5ca269c0db89a" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 160694272, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 78464, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 160694272, "byteOffset": 0 } ], "md5sum": "66baa8abc7e0675bea840c71fa31e705" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 20086784, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 78464, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 20086784, "byteOffset": 0 } ], "md5sum": "9904aba041af140a789416cab4d8f410" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ac88dbeb87e5d627afbd24bec1bcd589" }, { "dataPath": "params_shard_4.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": "6e4f5cbaa2f83c8f4447f94f4ba5e0e8" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 28557312, "records": [ { "name": "lm_head.q_scale", "shape": [ 78464, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 20086784, "byteOffset": 0 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 20086784 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 20094976 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 22913024 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 28549120 } ], "md5sum": "fba406bef7213082a3f08858cb7c60bc" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "df8157f6669deb37bd582b46d2d27e1c" }, { "dataPath": "params_shard_7.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": "bd02ce6fb12f828cb90735822daea4b5" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "9905e564937a1960ac483a648d1f5767" }, { "dataPath": "params_shard_9.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": "7973d164c09e3fc66fdcd6bbfc7357c2" }, { "dataPath": "params_shard_10.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": "c23b7b1505521e51876bb9276e45b8dd" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "6a9224a70be9576cdaa8d8f0d4212f82" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "ec201ff8dc9bca1876fad90622b76606" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 45088768, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 22016, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 45088768, "byteOffset": 0 } ], "md5sum": "a69f7a14ddd3c64d58d1d8741a72b2c6" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "8779045edbcba557d14908c4dad374e3" }, { "dataPath": "params_shard_15.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": "401d039a9b062dded03d005e30fcc079" }, { "dataPath": "params_shard_16.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": "fbb5262bddf98f8069aabcd2071a5c90" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "b1ed59d265e1e0c769d8d58fdc00e065" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "caae31fa6ba6af45adee05f57fb0e298" }, { "dataPath": "params_shard_19.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": "9901e37bb8468b0f002fa8ef3ddf10b5" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "2b3477ba266b624c61871b3ed730bee6" }, { "dataPath": "params_shard_21.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": "30a85d4039f27be01d047cca52c5bb8b" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 21233664 } ], "md5sum": "38b61d0cf39d5b54ff1bc749f7801924" }, { "dataPath": "params_shard_23.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": "e040861ddb56892ebc3006a933922ec2" }, { "dataPath": "params_shard_24.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": "183679ca291fea5397d6525d8b452b11" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "ffa910fdac97f7149ab3bd5b114d10dd" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "8186fb7578a2f6851382316ef7124791" }, { "dataPath": "params_shard_27.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": "ad8427fe55070b89c8683e898e45985d" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "d642fb42111f6ebe059dbf9122d3ce7f" }, { "dataPath": "params_shard_29.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": "22eca031e514809aa023885375f217e7" }, { "dataPath": "params_shard_30.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": "9eff873a83fbf320684ca8281d8c1d70" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "e0c85ab13df1c21c283c6c9dff1677bf" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "29a9a197bffe054f2742f97c647a07ea" }, { "dataPath": "params_shard_33.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": "85e1935ff115880633922b0844e3fddd" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "df8e4265f04a9d44d098c85bb538db0b" }, { "dataPath": "params_shard_35.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": "9716762d857002f620c74075b105c344" }, { "dataPath": "params_shard_36.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": "1f9dd5b02d545c67798ddd491731e038" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "8c189285151066ebc6986a680ac87765" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 33030144, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 21233664 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 31719424 } ], "md5sum": "a2cbe1a7d6ff6e2b1fe8fd5224891ea9" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 31989760, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 8388608 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 9437184 }, { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 9445376 } ], "md5sum": "c4d8f195c9c85460c4272addfc5356f8" }, { "dataPath": "params_shard_40.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": "216c6f811a7fdec41eed02b499e120b0" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 28196864, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2818048 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 2826240 }, { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 2834432 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 25378816 } ], "md5sum": "4040b0244589c0aa3ed7210d0b910d33" }, { "dataPath": "params_shard_42.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": "f964e05b31c484f7241185bd02fe6ed6" }, { "dataPath": "params_shard_43.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": "3b4291afb2021253073f4c01e4a90710" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "1708b6a701eed4d246d438530621df5b" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "5ac4c4c3f04ec4fc719052ced0092b0d" }, { "dataPath": "params_shard_46.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": "bf674dd28f3540ac6a530ccbbb5f96b0" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "ae24f44626959331d583719438996d49" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "90b1cb1c1c4fc4de3b949e732bee8776" }, { "dataPath": "params_shard_49.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": "964177abc17cef5d85d9d74333c02832" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "075c72bc6ae77422bc13654d0d6dd875" }, { "dataPath": "params_shard_51.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": "acc597cfdc53861230514f2b6da49df7" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 31014912, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5644288 }, { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 5652480 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 28196864 } ], "md5sum": "1ffbaa4a9e09ba47e5ece34e52dc5687" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "6c10a6e62fcec22d09fa9394558107c3" }, { "dataPath": "params_shard_54.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": "62c0d61c865165fc6f9f795ee4253f37" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "80e1ccb2b777f878ddd273fe9dda1ec2" }, { "dataPath": "params_shard_56.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": "1b50cb3163e856152149cd1f7b342362" }, { "dataPath": "params_shard_57.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": "488a285a61c558a8104a1d9eb6b574ee" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "52604b9b6316314bc931dd1686020b54" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "142f6d9628a5c8233ec6f1c65cfa2059" }, { "dataPath": "params_shard_60.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": "b4500c14f5733ed6c3513b0d60aeed5a" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "78cbd66700fa8efa29b632dde7620667" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "8c3dfaa22082b3b661b833ba5a2af41d" }, { "dataPath": "params_shard_63.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": "7a6732c9f8728dd47ca071d0adab6b84" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "70be72d1dbaff50c96613bf3cf2f5282" }, { "dataPath": "params_shard_65.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": "a572915405be9dc9d322885a74baecd2" }, { "dataPath": "params_shard_66.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": "9105e4b5a247490c6535b8d3f7a23e88" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "53ad8896bb53b3332cdbe5ac3ef0d352" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "351a62fe2e48ebba95c8eef86b152f07" }, { "dataPath": "params_shard_69.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": "3b47896c05b0378720a326b1495f8dc4" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 26877952 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 26886144 } ], "md5sum": "943975e885a096213bb9e03612a33050" }, { "dataPath": "params_shard_71.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": "de83f9bd90947d9cc324c9487c3c2104" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 32514048, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5636096 }, { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 5644288 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 16130048 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 17440768 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 25829376 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26877952 } ], "md5sum": "f65729b6a4e6a8f9199ecab75d63b628" }, { "dataPath": "params_shard_73.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": "ffd8f1010d3506e71cffd7b3df5f29ff" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "3e6254f09e817098c6ec7728abb20783" }, { "dataPath": "params_shard_75.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": "c8093df16a84dfef4f15e4bb7aec6439" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 32538624, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24059904 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24068096 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 24076288 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 26894336 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 32530432 } ], "md5sum": "d18e890a72b361a4e3424c9dbacf4373" }, { "dataPath": "params_shard_77.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": "04145648432506e07178f64415185f70" }, { "dataPath": "params_shard_78.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": "2b4132ec5d02d878b9dbd51f94888436" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "1b3fa0d80655a86a98dc690a31c6e323" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "e83a463d9558090c939c4791a4686527" }, { "dataPath": "params_shard_81.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": "97c5fb3c789056c7fd4dc28cd2f6fc26" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "13c2c1e4b9e2f2d0c71d84f29daf3f5e" }, { "dataPath": "params_shard_83.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": "f1a095b7b99471fd49ebd36627f3e451" }, { "dataPath": "params_shard_84.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": "7fcae64310f24ac4f8835532a16ef5ba" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "565c0f6f9c45ace93851ff0d28f13f84" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "09cce13eacb7e515c27cc9947246a201" }, { "dataPath": "params_shard_87.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": "6b6b6b2b074048ed864d7d2a7d338af3" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "76f1fef1cb65eb3f1b1a17cb025395ba" }, { "dataPath": "params_shard_89.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": "7eccbfeb6ada5afa571790d7636788c3" }, { "dataPath": "params_shard_90.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": "812c181ad81e1dcfe5eaa520acc222c6" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "e2c44a4b4428f5999b39357ea8015f1a" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 22544384, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1376 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 22544384, "byteOffset": 0 } ], "md5sum": "893b256372c729a85e03be21d4cf7b2c" }, { "dataPath": "params_shard_93.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": "c34b7a4a55dd84964fab9a0f6f1063f3" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "80c40327b4ce262a59b8c3e1d5d8d038" }, { "dataPath": "params_shard_95.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": "6f4e42a085acf64c9797b590e966468c" }, { "dataPath": "params_shard_96.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": "03d64d8b91f80e22e81b016f6208d3d0" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 29704192, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 344 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2818048, "byteOffset": 21241856 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 22016, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5636096, "byteOffset": 24059904 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 29696000 } ], "md5sum": "a3df035546bf4977127d75ff70622cb9" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 21241856, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 5120, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10485760, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 5120, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1310720, "byteOffset": 10485760 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 512 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8388608, "byteOffset": 11796480 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 128 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1048576, "byteOffset": 20185088 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 21233664 } ], "md5sum": "3e6cc1624f600e010d438cdfcfd1c2f0" } ] }