{ "metadata": { "ParamSize": 325, "ParamBytes": 3274754296.0, "BitsPerParam": 3.617639364354173 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 52739296, "records": [ { "name": "lm_head.q_weight", "shape": [ 32002, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 52739296, "byteOffset": 0 } ], "md5sum": "5e4907996c1059a42b222e6d6ea5162d" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "9f7fa49b1667fd826bc6d76d60aba9d5" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 33068956, "records": [ { "name": "lm_head.q_scale", "shape": [ 32002, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6592412, "byteOffset": 0 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 6592412 }, { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 6600604 }, { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 30128028 } ], "md5sum": "c4023df7fa9351bebeb3fb69a1f3ccec" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "f6abc61167dbaf0b7727fcafd993067d" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 32391168, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5914624 }, { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 5922816 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 29450240 } ], "md5sum": "8357226448f61fabe44876d47d43463c" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "5d637f042c774b7a4ad82b7aa44787c8" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "68eb18697b81d25190727a0af81508ed" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "f60e8bbc234ed43036b1fdd512098944" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "cb0a1b86d278118518f17d607673377d" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "7aa367974d3508737469196b38ce1bae" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "f6d3dfe498d0f460d9adccb2e68b6679" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "0961b48c7aa34f3ac76710ba3cdd729c" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "4160688c994821014b5c294661f9b9e8" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "60e5615ea17047a0793738b71d1695f6" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "7b243b8c02bb5e523743d3af1d38b1d9" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "78ced8b6ef54258dae04c1dca8e5fc92" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "ba899a9936d049eda7fa4cf5199621af" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "ab8303ce885f8054fb1ee7ccda5e9088" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "9cf70f59dc0dde75308ff6af1f0b3ab7" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "c9d3c6e4c8f5ea10b21b0ea3196a3dda" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "7771465512691efe3fb268d815fe64b6" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "2a7f9b98ec9f4b3d93a3917c75f1d9b2" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "9ef8af2dfffca9d97acf49bb1ed0a096" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "edc7d89568a930c8d8441579618fafae" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "b963a7dcd55ef9b00e8e88029f9d84df" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "67c70d5d08dbc1dfeb19797ea620c442" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "3cc913c45983a740c215c5b9bac52790" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "0787ea0137c084ea4787a8e19de78aaa" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "436cbfc19707f958469a5206a5980015" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 52739296, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32002, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 52739296, "byteOffset": 0 } ], "md5sum": "b81ac9f0b94deb3c6abccb84ee443ebb" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "c9545efaf52a8a41827aa77de0b2c126" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 31508380, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.norm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32002, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 6592412, "byteOffset": 24907776 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 31500188 } ], "md5sum": "b02fc1f1d2a9d06f03fd7b01c5092795" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "224a7466791783e582757d165f2f0a06" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "68ef526bd43678234a20590392332cf7" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "cb2fbcb96ee79b30937c2cf13c2bc5f6" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 30789632, "records": [ { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 0 }, { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 2940928 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 8847360 }, { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 8855552 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 18980864 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 20246528 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 26996736 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 27848704 } ], "md5sum": "c612a514696e66b98715d0b3adaaf46b" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "8f7c2220a45f39c65a08e0d8e7e0a52f" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "e4fed2a3d581bba6e68b52032caa4e87" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "c9e343d01830274fa4c201f51d69e085" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "fca11eee9cff2a6ab64929973c76f9c8" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "321a6666dfebb1613c74e246812352e2" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "7f0c83d46c4122e79dcdc0734ba3470a" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "22c5ebaac780fce7c1e5c1a2c37335ec" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "9856421a6ccd5ea2bd39f30dd11bbc3f" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "270517ab6196833cf2b384bf3d2eb7d9" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "77a7f30ba3ea096b62ee452fe34b085d" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "7297918280e0b22339e12453968ba556" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "e5e8d96d618c5fdc934252ab6525d2a9" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "5d4e62118425ae8e869588a06935557d" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "21e492cef7552bc05c234c9fe5981d3a" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "79b661b42d1c383918abb0663c1ed091" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "dde85c49747e5b9bd4955fd89ac16365" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "2a62aabcc3d4e8a74a6da5447e648988" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "41664876161f84155d5aa73ee002a338" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "810255b136e794f1b6d0329476ce520f" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "c0333bdb18da83aa0b061d65bac4b8b2" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "813a2bfc831ab0f86a37c57ea1864c20" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "44c9d81e789ede1e4000d73c946536df" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "9c96281aa6697e20377a8c47722d214e" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "b8eb555b56fdaca3ac8f51c84e24da34" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "1370db31df12091cde7afaedb652eda5" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "3dffa57eeb5a83b0c6f4ffe592989538" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "45f9b27db8f58c55da0e1cec599a3115" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f602830a7dab615727517b44f39038a0" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "20fa0f1e7de877f2e2f19c2f65f50467" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "bc35fdb9d4611781eb13a887f017e5b5" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "9c884f8773defb7fb3a2639ea63b3d93" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5bf780babb55e3c36cfdad541e7146a2" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "75c18cf81117056700e94ad878459747" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "4e0cd33bdebb6cee549804d7ddc9feb9" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "5ae572a9d3b8cd838a0a97947596624d" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "ecd7ea214aa80ae018f47eacca28bbef" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "784748bdb50225e85f18b4c4523ad4c5" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "55e35b5393c6b89fe5f3bf06b8f9352b" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 24899584 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 24907776 } ], "md5sum": "2070d5ea27efda15dadca9895d1abd8d" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 24899584, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 0 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 5906432 }, { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 5914624 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 16039936 }, { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 17305600 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 24055808 } ], "md5sum": "513fda0428a7be7854a20ea8bfcc4deb" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "f0c30da917a7ca70b6b3a1e3d465c4ec" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "712ef33929ced706408d01cbfe5579da" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "6c5b2c42b21ae4562c24c4b6f32d6931" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "5514bac39a7bc3bf4452c7bd49bf8144" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "81a90539d9c39aafee7afa683b8062c1" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "3f346e643df13965617dc258b103e8fb" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "9b2e67e7b5a5ec49476c37544a338c28" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "c4bf5dda6306b7ab218e72b34f0738cf" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "e42367c9c6fbe5512a2a2498b597b26c" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "19c464513b7a246a8c8167052fc4d11c" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "6668bc2b6fe3246684cda90e2a69f16a" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "73231cd30601077d5504d6b77f748eb4" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "094c06dc33d3b54e0e68b2e2d65dd7c9" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "2fd94b9345109e9286357d638fc40ea2" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "a311375c565b2220a444021ef7d5b3a6" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "e173658429d9bd50cb893c2b1273e056" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "b422eec1b1b847069953e3e4f153c875" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "bcde0b1b0f1e4a96b3e0354f76c3dd0c" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 23527424, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 4096, 1436 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 23527424, "byteOffset": 0 } ], "md5sum": "ee220e707a81ad436f550ac004cc977e" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 47251456, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 28672, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 47251456, "byteOffset": 0 } ], "md5sum": "1cc24f86418a232372a1b4b2cb2a80a9" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 27848704, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 18984960 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 4096, 359 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 2940928, "byteOffset": 18993152 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 28672, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 5906432, "byteOffset": 21934080 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 4096 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 8192, "byteOffset": 27840512 } ], "md5sum": "064a3e720b2b58e3cadbe9eebe0575c4" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 18984960, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 6144, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 10125312, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 6144, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 1265664, "byteOffset": 10125312 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 4096, 412 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 6750208, "byteOffset": 11390976 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 4096, 103 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 843776, "byteOffset": 18141184 } ], "md5sum": "4f2a911330246bc1d1707f7d489b6e05" } ] }