{ "metadata": { "ParamSize": 313, "ParamBytes": 4760885248.0, "BitsPerParam": 5.0011817065612245 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "lm_head.q_weight", "shape": [ 152064, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "f3f5b33e0e6289ea11129db20e302a89" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 34062336, "records": [ { "name": "lm_head.q_scale", "shape": [ 152064, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 34062336, "byteOffset": 0 } ], "md5sum": "225be214a903ed2aca357bf1e8ab5ef8" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "a2fc4dad2b2c67ed6356251e108d4c8a" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "7183c11e84b6b39e1658d4469b578033" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "a6a51d094ba3815aec743108fab151bf" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "fa817293164ee1e55f713e89bc1c5ede" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 33519616, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 4243456 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 4250624 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 8494080 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16980992 }, { "name": "model.layers.23.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 16988160 }, { "name": "model.layers.23.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 16997376 }, { "name": "model.layers.23.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 25254912 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 26287104 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 32709632 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 33512448 } ], "md5sum": "133fc7f073e6c5dafde60cea6a3fff51" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "5492d84ae294cf30c4e6a229bfaa2868" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "bdc8cf3b188ebc4d406f997c5bb6e126" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "217af82be9dce7d02d3d14afd399aef7" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 33512448, "records": [ { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 0 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 4243456 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 12730368 }, { "name": "model.layers.24.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 12737536 }, { "name": "model.layers.24.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 12746752 }, { "name": "model.layers.24.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 21004288 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 22036480 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 28459008 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29261824 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 29268992 } ], "md5sum": "3f8a5afffd75b818e1df7890c50f220b" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "26658197ce60bad3e1db73150e4e8341" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "8303128935ad1251d32db32a846d0060" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.25.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.25.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.25.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "3133c5c556ccbfcdd25ff5367560dacb" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "920c89f6a5946c839672f9ca474dd454" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "9ee785a3b000b0828f335f8d19c3910c" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.26.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.26.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.26.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "4223420e5de76ed5c9b780961baf2aad" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 272498688, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 152064, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 272498688, "byteOffset": 0 } ], "md5sum": "10908473392206d68438671cb41133b9" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 34062336, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 152064, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 34062336, "byteOffset": 0 } ], "md5sum": "5289c0b268de5174aa92387b68c10c16" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "6d12c2beab830d9efe623b77a579ca2b" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "aee1c4fee1423c3af9db8a9621e2e85b" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 29276160, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.27.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.27.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.27.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.norm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25025536 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25032704 } ], "md5sum": "a37090fc6c7fc5759e1703d6968dd2aa" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "dda52a2ed1a8b19f49ba0e51596eb133" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "8b61cc1247a51040b8cf8e51a6586b28" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.0.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.0.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.0.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "5de967b44b40ba7c5d07c05fa8ee8701" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "a87b96a4ebd16934869729dbf570b613" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "e375fd9ba692f095abbfad2ed09f3747" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.1.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.1.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.1.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "b6bb19b7d8c7315f4c00ee00a94cd226" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "7bde58de61ab4a6607e9cfe12a10c983" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "5f8085180a9a480b6322c653f6288412" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.2.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.2.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.2.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "774611c09c1e49523597b75afa563ac3" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "51154663bee30e5ce83cd08cf8338c91" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "8da8ae541c8d17ac072300d58df74b5c" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.3.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.3.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.3.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "d00a101310c8d7dc4a1db8c6468003cc" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "9cb90853ce8e0712c2d0c96c796f7de6" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "c582748d1b01522187390cb87f5cb96e" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.4.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.4.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.4.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 25025536 } ], "md5sum": "42b082779dbabe2e61861cf305bb821d" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 33299456, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 0 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8486912 }, { "name": "model.layers.5.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 8494080 }, { "name": "model.layers.5.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 8503296 }, { "name": "model.layers.5.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 16760832 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 17793024 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 24215552 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25018368 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25025536 }, { "name": "model.layers.6.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 25032704 }, { "name": "model.layers.6.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 25041920 } ], "md5sum": "bfab302fd7eff5efa4238507d0327d7e" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "79a98d76f819b4f28281ed180ca23a5c" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "d63aef35331252bc089a9c88ed976cea" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 30301184, "records": [ { "name": "model.layers.6.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 1032192 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 7454720 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 8257536 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 8264704 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 12508160 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 20995072 }, { "name": "model.layers.10.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 21002240 }, { "name": "model.layers.10.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 21011456 }, { "name": "model.layers.10.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 29268992 } ], "md5sum": "5abf6ceb845fde24676842266126ef06" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "7762c037496cf41c47f38f5bfa96d991" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "7f514b07294bd132ecc0802cbc84a02f" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.11.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.11.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.11.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "256e6cd800f4290905e9e55b5f080b9b" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "89912d6f89bd1f3c865cc1da85ec4ea4" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "eab67541a3d9c087e2d39027f7ee99c0" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.12.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.12.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.12.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "8a52f46f0e7c7633235fdc4f926ad9a4" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "2917ae26aa56784f5f57facd16203bd6" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "e61f3123cf8716b09a049cdf8512819c" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 7232512 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 11475968 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 19962880 }, { "name": "model.layers.13.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 19970048 }, { "name": "model.layers.13.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 19979264 }, { "name": "model.layers.13.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 28236800 } ], "md5sum": "930cce106be86e3c00b243fb2f7e4dfb" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "1db65d36cadd6ce6cf3867ab96eb9624" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "c58d8aef96d05b9dc0174213e1abbaf3" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 32250880, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 0 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 6422528 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 7225344 }, { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 7232512 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 15719424 }, { "name": "model.layers.14.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 15726592 }, { "name": "model.layers.14.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 15735808 }, { "name": "model.layers.14.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 23993344 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 25025536 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 31448064 } ], "md5sum": "a808524bfa883223f7944e4c4fb87461" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "b0fc83acbbc2963c11b2d8e8e9d277b4" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "96f368358576ed2712b8fc9d7306ad8a" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "a7f37f3954fc737c3d23d875554d480b" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 25484288, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 4243456 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 12730368 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 12737536 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16980992 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25467904 }, { "name": "model.layers.7.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 25475072 } ], "md5sum": "bb3672a00498630dceb73089d8dd52e7" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "6b8350198749363f440811da62f7e6c6" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "0834fd865c89ac434922aa17a0247f87" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.7.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.8.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "3e003282eff303daebd500cdc23674a0" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "0522f9c1f964211b0fd4998bfc77d005" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "b224b6d8743526f2322ea13326aec06e" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.8.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.9.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "a96ed2263e7250e048dd4e7c0ad23de2" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "75cd5a97414b11fb6032d47af58a5bb8" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "b243f01f5c1865f592e271cc2e8c2692" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "67e84f2dfef142af5470be7cc9a6d2be" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 33512448, "records": [ { "name": "model.layers.9.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16515072 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 20758528 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 20765696 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 25009152 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 33496064 }, { "name": "model.layers.15.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 33503232 } ], "md5sum": "838fdfbba94b0364c4edc09d5cbd2ec3" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "ccfda4369d7c64f91a950d56fe0fa477" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "0120330ea97d54ec3d0ad5bcd0b50933" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.15.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.16.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "8263cfaccdf4b163bf63497d821f6988" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "dc7c2e87e8c6bac7853a80786177880e" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "0f7bc397b04acc382422f3c1526d1da5" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.16.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.17.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "e738fed2f62d163cf1f44695c1b6e188" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "99a29981a79689ad01046ceaf93dec1f" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "cf458e7f6a2102ff57107c2b219b96b6" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.17.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.18.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "03f1d4766f5c7d2e81667b6c1c2fcc32" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "3314112b2c485ec508220e130d779441" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "bc8d427eb17f84989bb4dd955c2d30fa" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.18.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.19.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "5ff35de0058178faac27d5a7b4f4f5ee" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "de457fdaa9e5313f1fc76625efd94b6d" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "754afe9c7fdac7c8c37fb45a1e7539b4" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.19.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.20.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "d20899cab84c3c91d6acb3433cf6bc61" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 33947648, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 3584, 2368 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33947648, "byteOffset": 0 } ], "md5sum": "498d93ffb7778aafe440bbc7e54138fe" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "5c5436be99b156d6af6e83d78aa3497b" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 29268992, "records": [ { "name": "model.layers.20.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.20.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 3584, 592 ], "dtype": "bfloat16", "format": "raw", "nbytes": 4243456, "byteOffset": 16522240 }, { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 20765696 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 29252608 }, { "name": "model.layers.21.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 29259776 } ], "md5sum": "04b4f827aeee95c9c0cd4de5e1a121ca" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 67895296, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 37888, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 67895296, "byteOffset": 0 } ], "md5sum": "12449520ae4f2de427f638056845868c" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 33283072, "records": [ { "name": "model.layers.21.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 0 }, { "name": "model.layers.21.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 8257536 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 9289728 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 15712256 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 16515072 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 37888, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 8486912, "byteOffset": 16522240 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 3584 ], "dtype": "bfloat16", "format": "raw", "nbytes": 7168, "byteOffset": 25009152 }, { "name": "model.layers.22.self_attn.c_attn.bias", "shape": [ 4608 ], "dtype": "bfloat16", "format": "raw", "nbytes": 9216, "byteOffset": 25016320 }, { "name": "model.layers.22.self_attn.c_attn.q_weight", "shape": [ 4608, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 8257536, "byteOffset": 25025536 } ], "md5sum": "df22aec42b596db97856c61b57b7106b" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 8257536, "records": [ { "name": "model.layers.22.self_attn.c_attn.q_scale", "shape": [ 4608, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 1032192, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 3584, 448 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6422528, "byteOffset": 1032192 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 3584, 112 ], "dtype": "bfloat16", "format": "raw", "nbytes": 802816, "byteOffset": 7454720 } ], "md5sum": "292f3d72a22a3c6814374cf6138db903" } ] }