{ "metadata": { "ParamSize": 533, "ParamBytes": 9234108416.0, "BitsPerParam": 5.001536828453907 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "649985c16303220c3feb2c1ab98e3958" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "6159eb3f9201d0a97c05ce88c1f438b5" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "c55d7563616e2408783233c29b59f37f" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f7b9fd47971726428687bec9094a7bde" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "a54cd0b73c173ebdff1facbb138b7219" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "df2d9435ccb7238fbfe673497f484513" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.34.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fd7c0e03e4e79e7e9c30a3abdca25c8a" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 28891136, "records": [ { "name": "model.layers.33.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 0 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 10240 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 4433920 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13281280 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 13291520 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 13301760 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 17725440 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 26572800 }, { "name": "model.layers.34.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 26583040 }, { "name": "model.layers.34.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 26597376 } ], "md5sum": "150cd9e5264e4b7ac47f225f64798500" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "0957fb4b1dcfc735972a2d7583b2d79c" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "dc2a21f5125bfba0761e488219c8ce9b" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.35.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "808ee5c07f0b2637e3fed4b1ca6eca18" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.35.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.35.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "e716a897c4caa73de74c36b92be864d7" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "170683e448cd2e5b02c6f35477dc288b" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "c7d26bd1422a1b7cc6df9dba2f4c9975" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.36.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "6599096e0fcd1035b0a4f1d1795500a2" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.36.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.36.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "84de4886f570bb4d4cfa8c24ceef079d" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "fb170441648186906478a871aac6d387" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4272b6c4598cf616c6d753f57f48eba8" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.37.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fd4770b6be94d0ea59e1d6f1eaeb8640" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.37.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.37.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "690f0060f77fe036d184c51b4b4a834e" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "b226af8b0b22c658d6b077027320371d" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "fa59179157fc83b065a329d10676b058" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.38.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e79ab671caf246d6f44aa7cf93c3690a" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.38.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.38.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "de00f9cc569ea89d2df7982edb47767a" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "219888a802c48e7cf0c3f277cb3103d2" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "60385a82df164c7d1b9b41fe24cff123" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.39.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "a949e2d3d5482d2be9d288f1cd0d63a6" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.39.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.39.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "ae814ab1f96fa82d2549ccdad02306b3" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "ed7b752560ee88a212cc6f5250dbdd99" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "e9f3dde69a813b9fdc74979b156aee40" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.40.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ebf2204d90594763ddac78c62efcd706" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.40.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.40.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "8aa7feb6188f99d6677bd486125330be" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "2312091991c208d00e736ace3f22237e" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "9943d1f9cd218100ca08dde0e669ce3e" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.41.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "4e6697a3a0abc8ca649c000b307241af" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.41.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.41.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "9a23f0c303ba12265364c25f73023f6e" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "322cd01f831654b0256d62373697c92c" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b9f70cccfeebb598070f5a4066bbe6d7" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.42.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "83288f173d47bf0c6ab982561e583888" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.42.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.42.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "97991c418d0b895334e4b4eb6d62c8d2" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "0f4bade0ea5191364dcac3020fbc5077" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8c040727c0412a2598d4061df43e2f30" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.43.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "979ce445cf48359a65acd322d167177e" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.43.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.43.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "ed18711e2c0002640da19edb9c7e62f2" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "ff6ed5e7e905d13a0381382c941b4777" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3fccaa781d917549d81af1bd160327f3" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.44.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d52071e5dde2dec095af49bd83f04dc2" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.44.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.44.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c2ad3ad73afece34c35fc99f8a8a3cb9" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "7166eecb578678263f82c43fbb69e1a1" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "19a001023f2e034f2b6583963a57dbf4" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.45.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "fd4a656c7f0439b803aa5806ee838e9a" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.45.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.45.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "0cec3b70e6336fd66344095a7d8fc5c2" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "ab417120587f71420f020530d3a365e9" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d446a9cdb91668e6c599888023058cdf" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.46.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ce463aa147f0197f05dbf7d9b5778c80" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.46.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.46.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "4380b709dd6c93c3eda95490f19e6a46" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "993d98713f49cc2d7bc42da444c6806c" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a65e5abbcf61ddd4e512a91c84dd8fc3" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.47.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "5b3fc5215a3602deb6d297b921e720bb" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.47.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.47.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "f595efc480ac35f16323f4968e5364e4" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 389283840, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 389283840, "byteOffset": 0 } ], "md5sum": "72ad14250b0e1426d71308f71a6fc507" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 48660480, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 48660480, "byteOffset": 0 } ], "md5sum": "5b4b3f9d214d12d6553cc36f580c2f15" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "45083578eec5b4cb4c9c66a94623e7fc" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "ac4ec8374227962b6435310cde09ca63" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ff3f0637e8f63d72719d92521611d764" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 30355456, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.norm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14755840 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14766080 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19189760 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28037120 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28047360 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28061696 } ], "md5sum": "830449599f8ed9d2bca255cd47c3f052" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "30a28fc9212d1ea05944ffd8dd09d6d6" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "2999ae0d8377d8309992baa8dab269b7" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "97994feed7a70201870bde8f3183af70" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "019d12bbf763d55a46e5a6f82293214b" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "b5288d45be4bf5221053bb803e1a47e1" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "90092cffe7dd3da930b38732e213e639" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "08b4a5d46a3431f85c74394da5461f21" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "834d4f15454d85c1ddd4a64383842a88" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "8184c338d3a6e52ce85c74bbcb45a6a3" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "43a6ca1fe290f31ae88425d3c7398bc1" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ba3dc452bec8c6bf37f36bf1fdb9e7cf" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "818eb2c9071c757ebb5f46321fcc5562" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "4a0a336e10ea4087924d5a66c999ed06" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a346bf496899b0a83a4df935b72aba47" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "186d08d696b3bcacb9fdb6b5249b3cb4" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "2e17e721745df3fb04718c5761f608c6" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "910fcbfff4b69ab04088b2fdbfa75f0c" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "1e298acbfc366587e2fd735ec38b8a85" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "3fa48280c6387f2d04f4bf0bc424b640" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c41306fae9064628bd2346db9f1fdbc8" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "320d7547c0cd17f2275213f2e446e23e" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "12863d849a24c59730cd6201b7642724" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ed3725062c15bab034da3e8fdc604781" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "014b8cb07b99fe914835056660bafbfc" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 33110016, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 14745600 }, { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14759936 } ], "md5sum": "fcb5891f332fae109d957681f6137d04" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "739135a0db6b5e76cad2450fdb9e6c8b" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "0d026fa0d22a11128298fb56c259b7ee" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "d1397500de600a2945fc9ae8b8e5797b" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 32638976, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 17039360 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 17049600 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 21473280 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 30320640 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 30330880 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 30345216 } ], "md5sum": "63f92322490d077af5012b79325a022d" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d3ae33182d96c8d520ed9a4686ba6377" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a848742100aea4ffddd2f293f691b9ec" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "0882c26ad5acb84e959f7a0d516fcb6e" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "aed5ae4d02db18d73cdffd0d7818a84f" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "394bbb0f8f665f04bbbc2243dad7b562" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "3e15b09f2f33f5263befc53e882b037e" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "ebd974390d96f1dcba0986b1afcee543" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "07fdc3c2cdc08d45e4cc451fcf4c563c" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "217700fc6bf641221ca476cdd7434a0f" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "483586a3caa044b5a60ff24dcad771cb" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "bf031ff205e2434955f1e8fcbadfb08d" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "0553675ce39b993387c0e1c44609aa95" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "98cd2952b1c49a9bc5cd3bfb8ca4df82" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "d126ebc6cf7e2cb24de5b4befb2be964" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "e74cdc4bdd3e400d67a745108aad5966" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "7e413f63225afd56b22cf23eab30c897" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "46a03ba56f840fb1df743259e6ae0490" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "824d6beb67a6dbb5236722d1cb2d4204" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b0e9bb8bdc4517a264161cbf4b07ccd0" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "4af23fec5891e5284fb57e8c464b5ab0" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "dba845797eea7ae09cbbeda2f428883c" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6d8f77d8c551e83e613725d7124e4319" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b3eceb72af7a25111dc8f0cfaa83c41c" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "0ce69e68d218d33be9803e6ebbc0abca" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "a773b03a9a3bb5f50bef33954becce61" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "5e85556b42272d21f05a6de8defb03c8" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "9d0cccf1ed3821423bc408546d767726" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c222134cb9554aa485a7182ec39bdb84" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "970bad8c5edc37c5539efc3b1e97b2f4" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "985f8ec7cc2818c3878d3c1234392473" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "7d5745b2baf559a7c351365d8126bf6c" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "bca9acee9f73b82d765f4df8a9a30e2d" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 32471040, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28037120 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 28047360 } ], "md5sum": "22bc578b8bb6a18bff63a9ab9332aadb" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 29515776, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 8847360 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 8857600 }, { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 8871936 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 27222016 } ], "md5sum": "e71c53919af9f7e4f1a82820f8f602a5" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "5f3690fb1b2fdb7dcf305b5b125b92a2" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "47d126d60b2e793a7d7b0f51315ba169" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2230eb14e8934e6288530d60787f4b57" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "d95844af35c37e3235e14d2b7f8b0163" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "05e055cdb298bc2f3f5a70690f219c10" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "45392e491ad0372a4745ff75eb6210e8" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "666faa776da698bee8415e0e0881babd" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "16b22a73c3f7ab7a9b2d391d2fab2da4" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d709a0c6bed99017ebc7dcd1b1c789c0" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7d66a12f89f1d61de4f10d4c1b83058a" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "1ac9471c3912075cb8c5afc3f7aaa699" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "c26604ec148d8b9fbb4adb0f910f0ba7" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "0864ca752ceb7bc1cf6818b1dd80fcca" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "6d535a6c2622519d41979cd29c70df76" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "dd5b369081df5611dbe555e1823846e2" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "bed3b3195c22c40904b1c3072c318929" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "61591872e9ead6531e71498d5e9c11f0" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "37bbb84dee728473913e041a84a560c6" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "c0def3775fbe60cca7f9d3abcea75fb6" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "916850ccb5ff35e626f60ed7d8f6f812" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "74a77bc482b347129c6d4f159d7219ea" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "4355194c420aef7a8cd11a688ce9a5bf" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "546cc89f3eea5a556a23323b5be4d318" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "40bef03b0e2b6457314a00380ac40303" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "6160e286b8deb5fa5c9c130c54ab0818" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "449a2e3ab07b9532e56c2c05e5e23455" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "24c5ecc813f95c702a1f2b070a6e1e39" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "8e278b4545abf07b6b9cde031ac81f55" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "325f79964eb4b0ef4170d693cddc2b16" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f0cf1b7a5d96930096af522ae9ded5d2" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "b8ab6acfb4b0f270935ea1bc19c08d9a" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "63a1824e742685711f061b19a99a85dc" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "85a3d3076f0fdde561066d4bc84a2ac3" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f2f364bccadb913bf72f37df3e56a76f" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "582b3c401d079a799bf3dd238048737b" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "4bbeb2166d70bd8d0a17b37e691aa158" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "409002be961fa2135227b81a0b7f762f" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "7a05b2fbfea2f301f4f7b40f60e42627" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "113caee19bd6e5ede539727e04cda00f" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "67033aeb3158b0211ae34c36248ad234" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d761c3dea821f3dce4c5fb4bb758581c" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "db8e7b90207c0ab861766fbc451bfe8f" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "bfcf41433e500bbba3f13ef2895bb309" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "b526e80ed343894250cb36cc2d7d11a9" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "ca4ff71f5368596bf87174a06a7e23b3" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "b4c4c718944dbac4a3085253c582ada1" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.28.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "99be7447271b7eaf3863a14413b762db" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.28.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.28.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "2c651af3a613eed4904ecb79da3cfc04" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "15ae211390387079c82503b743c02584" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f8a8ec85186083025ea216b71e042905" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.29.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "67745f75c9f70782f2a9d5234bacd37c" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.29.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.29.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "12e9af66b566eef9b599043b5f41c372" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "16e597b425e9f6ab30cdf02aa7326fe6" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "f0fbe23614b91d89b1ad030c8986dc45" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.30.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "859dbe4f7cd79506f79b7cffa126a833" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.30.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.30.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "36f5d28ce92deed75fa22ae8b363f5ba" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "10bbff516c6c5ff8df159eb2b426439a" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "a353885235e95fb04b33a469c67d61a3" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.31.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "2f904f24235d766f5af71c6d41dcfee1" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.31.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.31.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "9e56aeb02ed90a9f13885eb2dd286fa2" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 35389440, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 5120, 1728 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 35389440, "byteOffset": 0 } ], "md5sum": "d9d5e61482bade74b7bad90093223fd6" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 70778880, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 27648, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 70778880, "byteOffset": 0 } ], "md5sum": "8cef51213c4b7c47a1ca660e97406714" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 18350080, "records": [ { "name": "model.layers.32.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 0 } ], "md5sum": "32103b48d9a92ebf4b9cd3e3ce40563d" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 30345216, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 14745600 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 5120, 432 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 4423680, "byteOffset": 14755840 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 27648, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 8847360, "byteOffset": 19179520 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 5120 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 10240, "byteOffset": 28026880 }, { "name": "model.layers.32.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 28037120 }, { "name": "model.layers.32.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 28051456 } ], "md5sum": "591fd91c5c8201c87ba083b535057da3" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 33110016, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 13107200 }, { "name": "model.layers.33.self_attn.c_attn.bias", "shape": [ 7168 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 14336, "byteOffset": 14745600 }, { "name": "model.layers.33.self_attn.c_attn.q_weight", "shape": [ 7168, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 18350080, "byteOffset": 14759936 } ], "md5sum": "ce19fd0b3dc0fdde02e78876a8bd0dcf" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 17039360, "records": [ { "name": "model.layers.33.self_attn.c_attn.q_scale", "shape": [ 7168, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 2293760, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 5120, 640 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 13107200, "byteOffset": 2293760 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 5120, 160 ], "dtype": "float32", "format": "f32-to-bf16", "nbytes": 1638400, "byteOffset": 15400960 } ], "md5sum": "d5e6f83a8846b4429f3199bdc7e4ad12" } ] }