{ "metadata": { "ParamSize": 805, "ParamBytes": 31776318464.0, "BitsPerParam": 3.04023285660184 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 420679680, "records": [ { "name": "lm_head.q_weight", "shape": [ 128256, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 420679680, "byteOffset": 0 } ], "md5sum": "79cdbbd110de7ccddb1a2f1e20de7ac6" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 52584960, "records": [ { "name": "lm_head.q_scale", "shape": [ 128256, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 52584960, "byteOffset": 0 } ], "md5sum": "3b30e9c6343f50a2014db07dfbe274f1" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.78.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "73afa85da1905264dc494d9e6b27fe4d" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.79.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "fea5dbcf103f48516c8f992cfe9c9575" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 23560192, "records": [ { "name": "model.layers.78.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 0 }, { "name": "model.layers.78.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 16384 }, { "name": "model.layers.78.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.79.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23543808 } ], "md5sum": "3f3e891011ff2117488cdbb65bd8b20b" }, { "dataPath": "params_shard_5.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "1d69e1a70629f31d4d7b3906b749a2ca" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.79.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "72598d1cd490b1c5a3423a7c56609137" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.79.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "1ffaa645f81e45117969cecf8d61627a" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.79.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "dc90cceb96db03b52d379ee6f6a3b52b" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 420679680, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 128256, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 420679680, "byteOffset": 0 } ], "md5sum": "8b8a02a0c14245a32993c53a4df286b0" }, { "dataPath": "params_shard_10.bin", "format": "raw-shard", "nbytes": 52584960, "records": [ { "name": "model.embed_tokens.q_scale", "shape": [ 128256, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 52584960, "byteOffset": 0 } ], "md5sum": "8c3f7f6a3dadd8a3303d0c97575306d9" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "7f8b25a32cc9aadfd2c87f0c0e59bccc" }, { "dataPath": "params_shard_12.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "aab0ca339f72c50187d60563bbd7318d" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "c6ff248935c2a0444ae2dd7c271ebfee" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "19a47b56cded04eea6bd8c59333d173d" }, { "dataPath": "params_shard_15.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.79.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.79.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.79.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.79.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "73c4d00dd11db7bb97cca6cc8a4df70f" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "d11d3db0404829f9a95ad8626bee65a2" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "eee14a06a7ff8af2a8a40e956758fad4" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.1.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b1c8cebefc9c968a444e9167da2658b2" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "acb6d7c6b6cad9bdbf93ea365149d943" }, { "dataPath": "params_shard_20.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 3358720 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26869760 } ], "md5sum": "bff83f5d3bbf0c238c3aff0f71fc7c22" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "8fd57c1ab7c515ccc9d180251f05e96e" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "3950726b590b1cf44e282aca0cee203a" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "d4bd3675e51b116621a8a011f6d699d5" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "7893e49b7700cedd34b78f0ded01211a" }, { "dataPath": "params_shard_25.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "bb9076571ea32f2b22768019986360f2" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "e9bd9281a3528e7de2f40529c184e050" }, { "dataPath": "params_shard_27.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.1.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15138816 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 15155200 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26902528 }, { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 26918912 } ], "md5sum": "8cefd0e01f539422ecd756f645029cff" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b9e8c1fed47f5ed78084f975e257e6b9" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ed5351207ae2d2f93434474176bc60d4" }, { "dataPath": "params_shard_30.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "30c9135385eca92a09052d4a1a40a11d" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "52acf9ad2eb65cbbead8833ae08ba4ff" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "560e4911bbdb076d77ba9b7c7d824fe2" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ef1901213aab8b10d5f3846b5e648fd2" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "77423014c7b04cc8269583c2f31c712c" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "34e3abf0288ff2556dc3d426bb4337fd" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.2.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.3.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.3.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "13fd53f828807211798fb01ff489c6ef" }, { "dataPath": "params_shard_37.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "77a44838a2538159967ed4e986d45083" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "74136ce030ad261791a4b2f4a8a33c25" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.10.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "972d38d1ec185f63ceb2baff1a643d11" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "657dad5739760faf063989ea173a0864" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "ae3b24e223102febc95780075a2647d6" }, { "dataPath": "params_shard_42.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6626430a4961902989c450819a8208b5" }, { "dataPath": "params_shard_43.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "bf76abfddc38f962757761b58c835d06" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a28391fcf030500e1ced11075b08db7c" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "4bb1ab4e35c086dffb10b2214dc16d23" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.11.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.11.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "27a675ae250b21a7debdcac72e157608" }, { "dataPath": "params_shard_47.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "1fb0d9f80999338b005cf740b0d1997f" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "7034ceb1471d7bae370eed99753368cd" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d42e207414d06ef06202a524048e8cd7" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ede5f88a50c6708023f9ab7d8806653c" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "1bd0479b9e5ea6bf744ccd0aca10cab5" }, { "dataPath": "params_shard_52.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "1e1559106ebe2e3dfc67d6ca8935b8df" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.11.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 3358720 }, { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 7557120 }, { "name": "model.layers.9.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 10915840 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 10932224 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22679552 }, { "name": "model.layers.12.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "7060216ec8e25ddad90cbca1e0f0a017" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "4554e588ce60dd0776a2f8f590aba283" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "7c6290747eb0837939e65b9684872654" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "2dc2d8498a8e729231ec2c05293a2a7a" }, { "dataPath": "params_shard_57.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "d16373f3773e88a201a761146f3227ef" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f79983ec7047f10d23edaff868355e6d" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.13.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "dfa85fc4b233ae245a00de31104d671a" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.13.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "4e279f740836b9f1601cdb8da1248a9b" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "42726d916108ca5eccb87f034cad8b42" }, { "dataPath": "params_shard_62.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "2ab51983af8b3308c8e43cf1970004cd" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "4107ee6fbc8ada79d728ad42d4af4202" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d827e6b3eb081af0fc7ca68b3dddf20b" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.14.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "733730caa8431bf71e3b08f2eddb1ce8" }, { "dataPath": "params_shard_66.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.14.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8883f23dc41d8b30be6a46c985884bd5" }, { "dataPath": "params_shard_67.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "e771f1d324e81284d2f85bcd8353459a" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "06ed877cc2761a7b68f1e7b1bdb56490" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "0c139f1cf2678ee739e77a6ed0560600" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "fa0ec91bf67686e46eed3a7a6405df98" }, { "dataPath": "params_shard_71.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "e0cc343e9d18554ffb9ac22c123a5e13" }, { "dataPath": "params_shard_72.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "5e8b568fecf31fa66dae3de8ad59de2a" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "1c62e8fbbeece15d69fa010101fd9009" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f75212c3073b66d6e43fdc2baf02aa03" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "e4ccf08bd8ce0d2a289fe1639b1a9681" }, { "dataPath": "params_shard_76.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "15434de9ef0a03014ac6922b152cab18" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "82ede31818a5ad43c679755818cd1eda" }, { "dataPath": "params_shard_78.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "2a1e45ddd474e838bdf9a0e01e9e83bc" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "6b8eef6484c95ae8a1eb9c743bcafe1e" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "38f347e549881ec4705dcdbf9f11e15a" }, { "dataPath": "params_shard_81.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "116bc51485415aeaa3760cc74b3837c1" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "557b36a7739a2ccd3320595ca7ba1ef9" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.16.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.16.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "48c634e846ad22e37e66f11edc0909b1" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "fce103e779fcf2fc25e605ab0b9719b1" }, { "dataPath": "params_shard_85.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "0e96004e82864c3a44fb0aa566ad272c" }, { "dataPath": "params_shard_86.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "e41c80aab30b365fcbf2261902b12ef0" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "8aee3ca82772e10ed899a75a182ecfc1" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "9552c968bbd9d7cbf71bfdbb5c32aca2" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "2a4f64366952c05c9f7b4090d082fa05" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "55d87dd44a6d4153fe807481ceae10eb" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "044fc57468a87eed6d5b9b1f27f53e13" }, { "dataPath": "params_shard_92.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a504fa51980120b0dea15944c174353e" }, { "dataPath": "params_shard_93.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "dfba4273d180d805f1c26a52b4ad4cb5" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d8e3b6eb73844418284e411fcb215940" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.20.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "8757948dc951c523a2c7f8cdffb35420" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.20.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "28d19ccc96b3480b6ad84971607c9d41" }, { "dataPath": "params_shard_97.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "811b2a6d6494701b3f2c5b4c75dc1f65" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "0b5c11cd5febae92836f7abfd2233d5d" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "409b1146445b3ec3395477bd50ae31d1" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "b136aaf524bcf1e64e0e0bb8be4d163f" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "38fe372c888a0e55f78670ea65bd162c" }, { "dataPath": "params_shard_102.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ccdd3faf44a28fd66ccac9ed1438710b" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "89247e3964cd17cfb39d6e5f81cc4f3d" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.21.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "bae35fb14b2e3417dc1568c6fa159127" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.21.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "da1bcedbc7af6f1d95ea23c485402166" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "3f6f010ec02f644ba41790347c24f309" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "d1ab16f4899c40176bd0559cb52620cc" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "d5c980b81d56bd3716e105cd09427b8b" }, { "dataPath": "params_shard_109.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "890932abedb47da48c4aeaf77d6850b9" }, { "dataPath": "params_shard_110.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.22.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6040914fd07bf53d6a865963e8543e56" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "5338d53633a4664ffb1c5b6067b84f53" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b782df8b4fd6a6a4d49b820386e46524" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6783b1a38db73a66450572fa80abd038" }, { "dataPath": "params_shard_114.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "919c1f404a543b91b388961e0b3c9222" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "bf73c81ca01a9ca68c9a33a5bef6801a" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "2ecdb3ad81bbd5f299d7740ae66ef0e4" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.23.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.23.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "847c02737b894f8f1fa15381a32e4b5f" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "767cfd5e3921ef9528d6ff2fcab36be6" }, { "dataPath": "params_shard_119.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "3d31c061900a657fb26bc71db482a82c" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "33d787d60b7fa2bb6932eb90575ba68d" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "44800e0c022e224492528e44ee2a72fc" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "15582b67dac4f8fdc91b5850b8b736f7" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e1c15283254b90f5f7b7071e586da128" }, { "dataPath": "params_shard_124.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "1b27b8841e3d58d28f74ef0ad67ce2e2" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "73873fa14c0d9690ab5d97d26e258c33" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "dc799bed5066067e3e12e1b6627daa3c" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "414cbb6300129ec9a9d86d0327dfb4f4" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.23.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.24.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.24.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "039374e6388f810e54b0060ebea2008b" }, { "dataPath": "params_shard_129.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "0b31b640bcc95c439871debb05fb2b26" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "81f34db7fc818292f4630d0206ebf848" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "bf67d719623382151aab27cfc7e7eaf8" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "abe7c0a89c76991d579e9e138598a9ee" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "59c42d3ffb93b713eaa80cf41a7f1e0f" }, { "dataPath": "params_shard_134.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "fbb56783657958f741befc81e5c58255" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "61abc2f2703a8de2727c9b5678dc9e78" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "fc5ba546e621fd7d196e8808220d68f8" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "31ad68dd4f8914073c010688027d7b15" }, { "dataPath": "params_shard_138.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.27.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "84f6dfe6a21846674a10d096467612db" }, { "dataPath": "params_shard_139.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.27.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "330b196b258c59fc58b34d51ffdba490" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.28.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b7928cdfc1370099217e29501fa14776" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.28.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "6297587dbbd0abe8b39ef64f9b8a1cd0" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "bfe95a9d453512b2e6df9f12c520a09a" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "51a60d2e23ff96a676597261187bd658" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "18904d992b8941ba6fabc70af54fe53f" }, { "dataPath": "params_shard_145.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "c7aad44c325219963f66ee5cfdae8f66" }, { "dataPath": "params_shard_146.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "9e070f920ca578585ab6797574a50c95" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "036e0ecc074ced034806b9bb4e917f49" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "5234ba0e1be023147060485fa0e89a71" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.29.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "bdf8f9257332b384867adf898332315d" }, { "dataPath": "params_shard_150.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "bb2085c7a09bbfc1f97ddf3531042e73" }, { "dataPath": "params_shard_151.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "197dec5bbf297aee089dad3b25870fb9" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "9c6f90b857cd79a3c642b2a9365c21ea" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "ff0bb771603f7cd9abef78cffc538b04" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "19203a078527f7756731c95d01d5ae5f" }, { "dataPath": "params_shard_155.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "d8455fc821167782b36d093563217abc" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "26c5cc1bd2067294788e43e47b3c78a8" }, { "dataPath": "params_shard_157.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "28b4123e235184465c7e98acacd837c8" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "2f1917eedf33690b7b4cb8a807d098dc" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "46316e9040239d462713e0d5d4af8c9d" }, { "dataPath": "params_shard_160.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "f67bd1df2853b51a8e551d03d092e9e2" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "f40ea5121e4d0c325c112e133493059a" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.31.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.31.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "d65a708e8cbf48c46ac3d7bd2685d9ba" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "5db234e48602acc8a5ada0e4a52924cc" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "2ea0e51323e65853b0c0fb548d46d941" }, { "dataPath": "params_shard_165.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "245ff2ca45128c54a060d149824a8362" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "f5bdb67257a8d0ec9783a318ee1e58ea" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "86acc0412c23c80669b732370f374777" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "20c105ee4cbd3c31fc96c17ecc560c46" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "e01bcad0105bfa6745812ff36aa15486" }, { "dataPath": "params_shard_170.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "79b84e83d19d148b79158e9ea5f22673" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "6f21ca093c9837e35a81757c2ef22bab" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "4971a35d6332f0eb661275c23305b329" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.31.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.32.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.32.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "16e0f7922ab7e78f8b86b6b63482f526" }, { "dataPath": "params_shard_174.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "be4e0a758dd7b59ded8259969a1d68ad" }, { "dataPath": "params_shard_175.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "8a9b9b18937edb39a2a359275ef6a868" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "bacec05aa7ec75fd7c8392ffe6d117c7" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.34.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "fa111b95be1e677e8b11c64fd5055ce6" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.34.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "17dc0633a62503a6b949acedd22c7b05" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "dfc09530d6f2c2bfb31b69a593025f96" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "bbf4d3e2c5231c260aa2da93f0a8e8da" }, { "dataPath": "params_shard_181.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "33792b7e0c0ee1ba0dae7973e9eb52da" }, { "dataPath": "params_shard_182.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "35265bb7012ae9434ed01be6485a2cf7" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.35.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "4aca80513a06bbc992c557a00fb5c7af" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.35.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d39e4b92b05390b409a5a8c83f28054d" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.36.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "207f4907ea1704d6d4e9e927d6a7ff4a" }, { "dataPath": "params_shard_186.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "49e50b2597b2408afd8189876cac8dbd" }, { "dataPath": "params_shard_187.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "6574e7c83ea56706f5f9d405662c5dd6" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "00563dc3d84838b21e73eec3b8e2ba0d" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "91c8736a199ccbf25e822965989e420a" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "5d3e27b481bfe6846d72dfc549ff8461" }, { "dataPath": "params_shard_191.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "11af5d4f1631aece0a6910c6992438ca" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "09190a20dc3c98dbefc34999e1b5a4c2" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "181463c091cf44b9612f82e73b252db4" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "7104e69e0e99c84e7a2381e21bbc3c3e" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "aa25b7c436049ef72550b663079a2f8e" }, { "dataPath": "params_shard_196.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "a6d1f4bddf59aee06efff4812a8581d5" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "8eb8bac431847c3cff1073c91a0781de" }, { "dataPath": "params_shard_198.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "cfe30a1ef82e78e26f0e52fce425a14f" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "ee5d08fb6bce0bb757323e34621741dc" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6c193ebe9758e5c43956f712a27e7e8a" }, { "dataPath": "params_shard_201.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "bbd26233a0b167f39e4cb504b37b5da6" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d7606c54081045ba45fea0dc92bf4c48" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "c2e1ca98b7748ce8dc80125be667b84c" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "3a10f801f546e74245df9314c315a7aa" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e97b4a84970a292885220b0e38d1e0a4" }, { "dataPath": "params_shard_206.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "aa83e2fe057a478a62f6bc1ee07334cc" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.39.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.39.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "6281cb6f33aeb77a8084e7fb5a7f3e57" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "c4d0087e3410f3dc7fc14fae946c89c7" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "88b2114358229e6968c43423a52faee3" }, { "dataPath": "params_shard_210.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "b716d0d619321e8fa87df19932ad2cf6" }, { "dataPath": "params_shard_211.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ea770c4b55a9ee2fa3d6cb902a9697da" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "f0c4f1819933e919a2b3e3ca3df0fe93" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f9ea880fe6c16b165a5eb9a8684b0094" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "be3e208ea9fbe3ef644bc07f7a728a6e" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.41.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "316a5103795dc7bd210d660f986723c3" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.41.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "35e08612d6db8a744e3c38ef5120cdc8" }, { "dataPath": "params_shard_217.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "88fe4aa2b32b6436fe25e8b44d7767e1" }, { "dataPath": "params_shard_218.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.39.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.40.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.40.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "6b9430683697ec232906e9fb20bd3ce2" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "a194f7bb6c9edfdd1205ecdda4c39428" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d2fa94c3d61a46fb92f90ef40cc4894f" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "489af120e1a665501194bda6563b4ea4" }, { "dataPath": "params_shard_222.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f8136254944e0e70f44d7d7ba7e24054" }, { "dataPath": "params_shard_223.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "249e781a11c6d9532355cff4c105dcee" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ad94a15d9ab0695acc54889543abdcb0" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "146c8bc753cc5ee9b1b9a96cea850c42" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "c3a62d9564c953486d3ddc04c89c3123" }, { "dataPath": "params_shard_227.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "45941108f09b68d900186c00aba2a94b" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "06e710a4e6ea3916b07bbe59a367a03d" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "baeb79f75b9ab4dceaeb2ab9b658aac7" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.6.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b60fdd552522027a671c38921ea0bf50" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.6.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8f9c6368777bc501ca0b9077a050d1d6" }, { "dataPath": "params_shard_232.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "06fa823c373a137caefa1a0519c14e35" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "bed715c96f069b24f17c46b0f6e83250" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19320832 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31068160 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "94f891372465568577d24d0d11f18913" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "37e5b208d8e02af2f21cb088fba03b74" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "faebfbdbdc772dee10f29c6e17f2e71e" }, { "dataPath": "params_shard_237.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "10324289083c13e446eb323f06604e3e" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "f0d22ba32d7ac290647e5300e1cced7e" }, { "dataPath": "params_shard_239.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "74922fa9a66d01ad977200d5cbb27cd6" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6cf196012e229f76303ab52a2d2c491e" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "6863ed98e66bb4042df4f98786db2999" }, { "dataPath": "params_shard_242.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ba48b4a862551a1e1eb21db4c922004b" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "8d7afe9b58ce7a229878d9b80c9d29e3" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.43.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.43.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "402e6d30b16daef35b91c69540b2acbb" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "c8bf53f3412f223b9e382f6a8853a516" }, { "dataPath": "params_shard_246.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "89b48ea6b70c8b07ec51c02bf84f9d65" }, { "dataPath": "params_shard_247.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "e43023d3d3e2d742a18d41e63fc0bba6" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "b595941e0febfec805dad92e87b80941" }, { "dataPath": "params_shard_249.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "0e479116e203772da3ceb8bb2ae24e9c" }, { "dataPath": "params_shard_250.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "6bba03fc6d27c49611571282c882a0ab" }, { "dataPath": "params_shard_251.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.43.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 3358720 }, { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 7557120 }, { "name": "model.layers.44.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 10915840 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 10932224 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22679552 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "fc94756a5a9aec91716b2f1a2eae1eec" }, { "dataPath": "params_shard_252.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "dda85b84cf5fd0ea915e48ccb8ce753a" }, { "dataPath": "params_shard_253.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "b110a651e266403ea92edb07226f3a70" }, { "dataPath": "params_shard_254.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "29c15be99e1359ad2f4f023b2bb139b0" }, { "dataPath": "params_shard_255.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "1272d48cb8a2f8be96fe82cfba6d8e8f" }, { "dataPath": "params_shard_256.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "75bcb8ebd2408201c9ab30bcf2f807c8" }, { "dataPath": "params_shard_257.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "777c765c7a1af35382672dab65e3804d" }, { "dataPath": "params_shard_258.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "1144ad87f491865586430b6d688a4e11" }, { "dataPath": "params_shard_259.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "0d3f1ba5f3d0d43071874b68c306bfe1" }, { "dataPath": "params_shard_260.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.45.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.46.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19320832 } ], "md5sum": "16a6affab016d42a28ec94d6e30c1cea" }, { "dataPath": "params_shard_261.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.46.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.46.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "f9a8320a43b2bb2f275f53af197730b0" }, { "dataPath": "params_shard_262.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "2213dac164533de1b3c0f30904de9d7d" }, { "dataPath": "params_shard_263.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "728d2a72e60c96048d8757874a02fe30" }, { "dataPath": "params_shard_264.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "b11c3f71b25764498a53b74e79b1a7d2" }, { "dataPath": "params_shard_265.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "c88506aaba44183d6df84a4d361a9920" }, { "dataPath": "params_shard_266.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "040c732d1d561c015b244b9e40a0109f" }, { "dataPath": "params_shard_267.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.48.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b0097fdc592c33c3516cd795ad887b59" }, { "dataPath": "params_shard_268.bin", "format": "raw-shard", "nbytes": 22745088, "records": [ { "name": "model.layers.46.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.46.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3375104 }, { "name": "model.layers.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3391488 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3407872 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15155200 }, { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15171584 }, { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19369984 }, { "name": "model.layers.48.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22728704 } ], "md5sum": "4fab0bed53a347c07db8a06cfe3a195d" }, { "dataPath": "params_shard_269.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "cb7ec1195eefa871d875515d5c7d37a8" }, { "dataPath": "params_shard_270.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.48.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "ccfe6aa0dae82846de4d0b18dbe394af" }, { "dataPath": "params_shard_271.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.48.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "4b3ee0e08045d658459dd4c697617e0e" }, { "dataPath": "params_shard_272.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.48.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "b110e4bfe38869fd0dc2a307471a1325" }, { "dataPath": "params_shard_273.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "8cd1ca77cad8a418e188853134f62597" }, { "dataPath": "params_shard_274.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.49.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d307892b2ffd48d1f6bf9a37e01d7b9c" }, { "dataPath": "params_shard_275.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.49.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "c0fa6ee6a47fc8432f69433ad5e9b860" }, { "dataPath": "params_shard_276.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.49.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "f3ab1dc7c843bab266ddf278118a0cba" }, { "dataPath": "params_shard_277.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.49.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "7cffe00103e964ad9a7ac8daacc44d85" }, { "dataPath": "params_shard_278.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.48.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.48.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.48.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.48.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.49.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.49.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.49.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "83ebf5b207f97051485fd611e2d08e74" }, { "dataPath": "params_shard_279.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.50.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "3a9107d68b48aba9f28f6f61ba96969d" }, { "dataPath": "params_shard_280.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "efbf40c3521af1971c4c9254ea8534ed" }, { "dataPath": "params_shard_281.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.50.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "9b71eb119f716f542fcde2273a33cc2a" }, { "dataPath": "params_shard_282.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.50.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "7df80668daf5f08a67b12b767b826a5a" }, { "dataPath": "params_shard_283.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.50.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "edf1d2ebb7838fa2246c98cdb97c2dff" }, { "dataPath": "params_shard_284.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.51.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "5fd789175927ab7c5cd1931434d78dab" }, { "dataPath": "params_shard_285.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.49.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.49.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.50.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.50.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.50.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.50.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.50.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.51.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "5a3cb81296c9a107c3056dfb10f1456f" }, { "dataPath": "params_shard_286.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "81bd2e5217f3b24051048faa3bd7ba4b" }, { "dataPath": "params_shard_287.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.51.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a707b6ca1eef3dfbef49c655e8a38189" }, { "dataPath": "params_shard_288.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.51.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a63fea962cee79dfb1303eb847f65f18" }, { "dataPath": "params_shard_289.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.51.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "76e64cbc0e07e1fa5ba51f99c933db73" }, { "dataPath": "params_shard_290.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.52.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "19dfe77405e442e7c710d4bd648d70a7" }, { "dataPath": "params_shard_291.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.52.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "15ef1063531fb566ed04306757f350a2" }, { "dataPath": "params_shard_292.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.52.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "459d170a7b147cdd0b46c041125f66c0" }, { "dataPath": "params_shard_293.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.51.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.51.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.51.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.51.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.52.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.52.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.52.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "1c7decffa65f466debf15246aa7d34ad" }, { "dataPath": "params_shard_294.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f95966390189acd6f90863537477b293" }, { "dataPath": "params_shard_295.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.52.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "41cb5bb91ef5a509969a4970aa5f5b22" }, { "dataPath": "params_shard_296.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.53.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "744e8e2c54a95f3475252da0655fe3a3" }, { "dataPath": "params_shard_297.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "0a8f876baefa316e53e9e90663d4f3db" }, { "dataPath": "params_shard_298.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.53.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "0658b6efb7ac5cbd626ad06be8877dc0" }, { "dataPath": "params_shard_299.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.53.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "4ac075ff11a12b39458bbe2531e7e7dd" }, { "dataPath": "params_shard_300.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.53.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d6382e4aa66038ec97caf207573956b2" }, { "dataPath": "params_shard_301.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.54.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "ae72177b00631fad04bd24c204712716" }, { "dataPath": "params_shard_302.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.52.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.52.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.53.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.53.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.53.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.53.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.53.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "b98b45b606596cf440114c8b3af73468" }, { "dataPath": "params_shard_303.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "5af5b2369730fd2b39869ef24b1f6bcd" }, { "dataPath": "params_shard_304.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.54.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "648cab0559350a81111fbb1db6b4e5b0" }, { "dataPath": "params_shard_305.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.54.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e3c0b6058dab6ca0196a1acc67b43d74" }, { "dataPath": "params_shard_306.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.54.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "e118d8c7adfbc9aae2fda211a8f1995b" }, { "dataPath": "params_shard_307.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.55.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b781cb4b812a55d924c0d6cf77bb187e" }, { "dataPath": "params_shard_308.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "886fa0be360455e0ff18982ff27cef12" }, { "dataPath": "params_shard_309.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.55.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f74fbf24019964166f2063d51b9459ec" }, { "dataPath": "params_shard_310.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "d3b7b62c037fcc6f7b41cb7fe57b6cae" }, { "dataPath": "params_shard_311.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.54.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.54.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.54.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.54.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.54.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.55.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.55.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.55.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "c14779f4408cdfecf96311a4680a4fe6" }, { "dataPath": "params_shard_312.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.55.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.55.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "e65ac71373ecab1fde6abe6fa8eae8f2" }, { "dataPath": "params_shard_313.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.56.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "cb0053f7163e9320952efb12797dce2c" }, { "dataPath": "params_shard_314.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "7a259312665ad6aa036031ac8f408a0f" }, { "dataPath": "params_shard_315.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.56.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a36f56ea4d75755a0e5aa9f6b85de953" }, { "dataPath": "params_shard_316.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.56.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e671438e6097c7109b845bd8b47ae5ac" }, { "dataPath": "params_shard_317.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.56.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "6274b508d0669005c02dab612862a3a9" }, { "dataPath": "params_shard_318.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6c69c7eba33f852ed949a9988199b2da" }, { "dataPath": "params_shard_319.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.57.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "b7ca576cbf672be908480f3c02fe369d" }, { "dataPath": "params_shard_320.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.57.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "5a042da84404d2c6d6adc62c7204ff50" }, { "dataPath": "params_shard_321.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.57.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "25200225ae8538c73cbaa81d172c1078" }, { "dataPath": "params_shard_322.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.57.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "6bfe7a5bc4987e6395d3373bf13dd77b" }, { "dataPath": "params_shard_323.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.55.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.56.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.56.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.56.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.56.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.56.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.57.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.57.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.57.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "9dbc5c3e1cb2d8f24e88f8bae8665000" }, { "dataPath": "params_shard_324.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.58.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "cdd05a3b8fa72b2722590682c31318da" }, { "dataPath": "params_shard_325.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "751e1950c44dca8c6c0a49d6c1674d8b" }, { "dataPath": "params_shard_326.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.58.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "3817f806d12cba763f41b13bcabe61bf" }, { "dataPath": "params_shard_327.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.58.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e1f3514df8130ff4305e68f917864b4f" }, { "dataPath": "params_shard_328.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.58.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "aa7207864ef3970b99fda49810e7384e" }, { "dataPath": "params_shard_329.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.59.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "1737a3142f9def8fbd6b54c83fda2616" }, { "dataPath": "params_shard_330.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.57.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.57.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.58.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.58.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.58.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.58.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.58.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.59.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "a3fb00eddae71d294b35189aedda9056" }, { "dataPath": "params_shard_331.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "0189be740712437c41b83f619bcaeedb" }, { "dataPath": "params_shard_332.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.59.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d44f64eec2d90e478bf715d28873b7b8" }, { "dataPath": "params_shard_333.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.59.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "762015935c4e0b5e58dfc83c5ef099f2" }, { "dataPath": "params_shard_334.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.59.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "e4c5959cc6794a66cf9e304b8fbaf9fa" }, { "dataPath": "params_shard_335.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.60.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "446b0c09cbc6e8dd4cae13217136a95c" }, { "dataPath": "params_shard_336.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.60.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "9951d3caa7255d44583550ed2a14d23b" }, { "dataPath": "params_shard_337.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "4667e0d02a83dd1bab4fb341b326102a" }, { "dataPath": "params_shard_338.bin", "format": "raw-shard", "nbytes": 26927104, "records": [ { "name": "model.layers.59.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.59.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.59.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.59.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.60.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.60.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26894336 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26910720 } ], "md5sum": "c0fb71c1bcca08c8d7035b19997a605c" }, { "dataPath": "params_shard_339.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "87f9b1ccec25a88ad6a85b25d078e746" }, { "dataPath": "params_shard_340.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "c1293b91143ab5ae0b6c9bf9f90462b7" }, { "dataPath": "params_shard_341.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.7.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6e4e75d2bdea5bdf85712852601b4e41" }, { "dataPath": "params_shard_342.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.7.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "2023ddf4527240a9f58099d0797229d7" }, { "dataPath": "params_shard_343.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "9ee8a7c22da25c3d7af7b9f6f7f84f21" }, { "dataPath": "params_shard_344.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "c6d6291d120982f79dde12fa7540cb10" }, { "dataPath": "params_shard_345.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "d99e6be5707aabfd4c63ce9c06b1c174" }, { "dataPath": "params_shard_346.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "23d1d03b5ebce3346cda87063f003910" }, { "dataPath": "params_shard_347.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19337216 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31084544 } ], "md5sum": "b563c3a24800396f720383d4855c53c9" }, { "dataPath": "params_shard_348.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "e8790c045a58c694ef741b15f2469058" }, { "dataPath": "params_shard_349.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "662a560332a9dede932e4c39922336f0" }, { "dataPath": "params_shard_350.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "953ba7a7cd61f13c163e52bf3ac1302c" }, { "dataPath": "params_shard_351.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.60.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b37237f68fc391314f6c037dcf6df226" }, { "dataPath": "params_shard_352.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "fde0853993310bd6005d4f8dd42a7536" }, { "dataPath": "params_shard_353.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.60.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "1f1e80cfdcdf264cc95ae669e97b6f53" }, { "dataPath": "params_shard_354.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.61.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "33dbc2cde8ac393aacecacd6f148a4fd" }, { "dataPath": "params_shard_355.bin", "format": "raw-shard", "nbytes": 22712320, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 3358720 }, { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 7557120 }, { "name": "model.layers.60.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 10915840 }, { "name": "model.layers.60.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 10932224 }, { "name": "model.layers.60.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22679552 }, { "name": "model.layers.61.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22695936 } ], "md5sum": "7306dd969da1c3ebe997b7249c6e0488" }, { "dataPath": "params_shard_356.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e1c9cd039ea87de7e0fab2e9082273c2" }, { "dataPath": "params_shard_357.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.61.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "abb8202049197d4073124d449b22f114" }, { "dataPath": "params_shard_358.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.61.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "2d04334289ae754a0ba8c8f005740c02" }, { "dataPath": "params_shard_359.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.61.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "dcacdc81d33fad9e268473a6ee88aed0" }, { "dataPath": "params_shard_360.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.62.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "b018e1310dd16a90eb0e12e97f5efcac" }, { "dataPath": "params_shard_361.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "b5fed6e979f8a62d0f71e9d10ccb4182" }, { "dataPath": "params_shard_362.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.62.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "683edcb23cea67fd3dc37932050ddabd" }, { "dataPath": "params_shard_363.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e4b0096a509cba19045562b1ce391222" }, { "dataPath": "params_shard_364.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.61.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.61.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.61.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.61.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.62.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19320832 } ], "md5sum": "1254dcf3649d3583c038ac244fd0847f" }, { "dataPath": "params_shard_365.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.62.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.62.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "f5f86152e455e7df4b1ba2993918d61a" }, { "dataPath": "params_shard_366.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.63.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "152f836ced39e8d4be6b26fd35f9a152" }, { "dataPath": "params_shard_367.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "99a448fb0f31e72d93afbba5aad0cbcc" }, { "dataPath": "params_shard_368.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.63.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "92d2d65dfd78d2929dbcab9103c07a64" }, { "dataPath": "params_shard_369.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.63.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "44a49955b5c02ae6bc604d4909fd0bf0" }, { "dataPath": "params_shard_370.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.63.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "9ebaf0819e18eca140e12190d346bc4b" }, { "dataPath": "params_shard_371.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.64.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "c3231c8afc65961385d88be0654caeac" }, { "dataPath": "params_shard_372.bin", "format": "raw-shard", "nbytes": 22745088, "records": [ { "name": "model.layers.62.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.62.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.62.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3375104 }, { "name": "model.layers.63.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3391488 }, { "name": "model.layers.63.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3407872 }, { "name": "model.layers.63.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15155200 }, { "name": "model.layers.63.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15171584 }, { "name": "model.layers.63.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19369984 }, { "name": "model.layers.64.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22728704 } ], "md5sum": "647b0ee82354fa4f10900672bdc3ba6d" }, { "dataPath": "params_shard_373.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "3eb99d1c90c0a53a9f095a49fc09fa64" }, { "dataPath": "params_shard_374.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.64.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "09c921a28614bcb7380128fc2e0157d9" }, { "dataPath": "params_shard_375.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.64.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a8aa673d5a001ba8fb9f86b5eb62611a" }, { "dataPath": "params_shard_376.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.64.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "b86b2994a37bb9c00731ef2d0dda539b" }, { "dataPath": "params_shard_377.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6210dfed1ea62936cffad1daf6fae108" }, { "dataPath": "params_shard_378.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.65.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "a8fdddd90db43512f731364f9aad279b" }, { "dataPath": "params_shard_379.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.65.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a854339a32af1f0c5ef51aa58eda688f" }, { "dataPath": "params_shard_380.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.65.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "38f53003a3609ada142abd21a6d28bc0" }, { "dataPath": "params_shard_381.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.65.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "296e824b39f20afe7d2654eb7363bfea" }, { "dataPath": "params_shard_382.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.64.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.64.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.64.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.64.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.65.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.65.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.65.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "c17c596b2739c1769996b534933b982d" }, { "dataPath": "params_shard_383.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.66.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "68d5042279e6ec60aa8944be6aa3c27e" }, { "dataPath": "params_shard_384.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "94eb47e929bc7aab401d3371c8bbac79" }, { "dataPath": "params_shard_385.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.66.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "241673a2708f5438b2ecf560edd6ded5" }, { "dataPath": "params_shard_386.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.66.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "f13735e836f79c8afb8df28b484fef8c" }, { "dataPath": "params_shard_387.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.66.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "5620a21ca85a0d7ff64d3fa8fbb00295" }, { "dataPath": "params_shard_388.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.67.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "99a0a843106946bd0d7ea335e223e7d7" }, { "dataPath": "params_shard_389.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.65.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.65.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.66.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.66.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.66.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.66.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.66.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.67.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "c59517d6689edeebb9b679f9a7600ff1" }, { "dataPath": "params_shard_390.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "2c1e9046d8b630c3289e84ffdc092500" }, { "dataPath": "params_shard_391.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.67.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "912d0cf53aec6185f39f63793a287493" }, { "dataPath": "params_shard_392.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.67.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "646d1b1f7e502c577883d301c7cc1ec3" }, { "dataPath": "params_shard_393.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.67.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "880bebebff9c1cca6429cdebc072e5e0" }, { "dataPath": "params_shard_394.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.68.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "b83c294c10c704b554190f599b2cdb1e" }, { "dataPath": "params_shard_395.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.68.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "5c46bcb9044420eb1a544ff3aa1c48cf" }, { "dataPath": "params_shard_396.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.68.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "d507bf4a646ded61091ce49bcd5dbfa1" }, { "dataPath": "params_shard_397.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.67.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.67.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.67.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.67.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.68.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.68.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.68.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "079f11849863c6ac245b494bb3e0ae70" }, { "dataPath": "params_shard_398.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "6fd4f1ca3b7ac1066d1ba8b2f33bc063" }, { "dataPath": "params_shard_399.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.68.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "4943762c16fa049047b11532fcb28cec" }, { "dataPath": "params_shard_400.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.69.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "e78d6f4d00ce09fd09ce9a2d14623793" }, { "dataPath": "params_shard_401.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "f10bd8b08e1bf71f052e8036a0ee79db" }, { "dataPath": "params_shard_402.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.69.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "9211825a8aec27805522c0235ad2d778" }, { "dataPath": "params_shard_403.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.69.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "7b3989eca3addb150345b7a641eddd53" }, { "dataPath": "params_shard_404.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.69.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "42b3290a330a22da61f070ea790b4522" }, { "dataPath": "params_shard_405.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.70.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "84d7ce8100278122933bb61ceced82c6" }, { "dataPath": "params_shard_406.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.68.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.68.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.69.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.69.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.69.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.69.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.69.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "9eb56e63f8d1fc81c43cc5e2905b1071" }, { "dataPath": "params_shard_407.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "07aac6375f7d9612894ddf3daab94f92" }, { "dataPath": "params_shard_408.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.70.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "bded2f04ef76d585d15cbc3a2ab4c745" }, { "dataPath": "params_shard_409.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.70.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6d16279eb95d7d3a8ed1b90c122d919b" }, { "dataPath": "params_shard_410.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.70.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "8ab51a22eac05f788b16588480cb6177" }, { "dataPath": "params_shard_411.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.71.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "73c34fccfbad831dae264c9c26da8269" }, { "dataPath": "params_shard_412.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "762623061e9801fbfa9b2379f109db06" }, { "dataPath": "params_shard_413.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.71.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "10f9cee642b8be8c72229cf6175734a2" }, { "dataPath": "params_shard_414.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "ae475a394cbc37b6d0f01b569a290b45" }, { "dataPath": "params_shard_415.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.70.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.70.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.70.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 }, { "name": "model.layers.70.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19304448 }, { "name": "model.layers.70.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19320832 }, { "name": "model.layers.71.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 19337216 }, { "name": "model.layers.71.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 19353600 }, { "name": "model.layers.71.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "9b986f4ccdd3d8652d4f6240ef8b5b04" }, { "dataPath": "params_shard_416.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.71.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.71.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "78ffcc950147d9859a41558994a25b1b" }, { "dataPath": "params_shard_417.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.72.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "9200787421ae6b7b2366eed844770e7e" }, { "dataPath": "params_shard_418.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e469ed30655dd20b7693ff7515956d7c" }, { "dataPath": "params_shard_419.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.72.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "cd6215285d09156a8654022ce4271b33" }, { "dataPath": "params_shard_420.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.72.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6dab4486bc615e050daba042e038b8a9" }, { "dataPath": "params_shard_421.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.72.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "d9c25e8fda3e0340e89655c4e5df3415" }, { "dataPath": "params_shard_422.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "e1be5e9905a727fdbe114df4f9396d89" }, { "dataPath": "params_shard_423.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.73.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "f3f77732e53f2a4505a0123f48b7e9cb" }, { "dataPath": "params_shard_424.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.73.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "e22c192922902fba9ad3fbc1437a9643" }, { "dataPath": "params_shard_425.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.73.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "55bcab4f47040d999b123e2dd8d32d84" }, { "dataPath": "params_shard_426.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.73.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "2120925b10523ff20a4273235fdacbb7" }, { "dataPath": "params_shard_427.bin", "format": "raw-shard", "nbytes": 30269440, "records": [ { "name": "model.layers.71.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.72.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.72.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 3375104 }, { "name": "model.layers.72.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 15122432 }, { "name": "model.layers.72.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 15138816 }, { "name": "model.layers.72.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 19337216 }, { "name": "model.layers.73.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 22695936 }, { "name": "model.layers.73.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 26894336 }, { "name": "model.layers.73.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30253056 } ], "md5sum": "a0e6891c0518c227c74637249a23f534" }, { "dataPath": "params_shard_428.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.74.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "3269b4f1a016fb81c930409747ff83c4" }, { "dataPath": "params_shard_429.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "eaf85026c17fd3d6c11ef3591f28d1c2" }, { "dataPath": "params_shard_430.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.74.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "75bc7026f230836b6575f66870012412" }, { "dataPath": "params_shard_431.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.74.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "288cfa3562e13e2db1eda557bc8e5a6b" }, { "dataPath": "params_shard_432.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.74.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "287269deac3d37fb6ee0070b207497e6" }, { "dataPath": "params_shard_433.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.75.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "3874921a218ef383945be2b5f30b06fa" }, { "dataPath": "params_shard_434.bin", "format": "raw-shard", "nbytes": 31117312, "records": [ { "name": "model.layers.73.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.73.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.74.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.74.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.74.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.74.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.74.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 }, { "name": "model.layers.75.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31100928 } ], "md5sum": "bcf1bb95ce730782806ed46218e58935" }, { "dataPath": "params_shard_435.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "cbd384c04400d8096923ca8718a8b2fc" }, { "dataPath": "params_shard_436.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.75.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "0d43411773653ebcfd3110c5a116d583" }, { "dataPath": "params_shard_437.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.75.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "a67b2f3c5fe028d6422373ed2c72cd5e" }, { "dataPath": "params_shard_438.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.75.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "3f9d2ce23bd31e5ae8688ab323561179" }, { "dataPath": "params_shard_439.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.76.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "6e7a78abdba3445d672b3d70a9dfef10" }, { "dataPath": "params_shard_440.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.76.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "26a993446541ac84d90f0532645d0096" }, { "dataPath": "params_shard_441.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.76.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "7bdc9b1f3c4e4a3ddfda571eff97e015" }, { "dataPath": "params_shard_442.bin", "format": "raw-shard", "nbytes": 26894336, "records": [ { "name": "model.layers.75.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.75.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.75.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11763712 }, { "name": "model.layers.75.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15962112 }, { "name": "model.layers.76.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 19320832 }, { "name": "model.layers.76.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 23519232 }, { "name": "model.layers.76.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 26877952 } ], "md5sum": "4ef3fd46bd28ac700e3de2df00982741" }, { "dataPath": "params_shard_443.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "4b9708a470c627b39afa81b0835fa35e" }, { "dataPath": "params_shard_444.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.76.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "5b12a93c61c7b1331170ea937b24343c" }, { "dataPath": "params_shard_445.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.77.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "7045fe94e8f2233f001440bd858f48ae" }, { "dataPath": "params_shard_446.bin", "format": "raw-shard", "nbytes": 188088320, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_weight", "shape": [ 57344, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 188088320, "byteOffset": 0 } ], "md5sum": "b664affea57f5fe94adf02f2348c0941" }, { "dataPath": "params_shard_447.bin", "format": "raw-shard", "nbytes": 23511040, "records": [ { "name": "model.layers.77.mlp.gate_up_proj.q_scale", "shape": [ 57344, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 23511040, "byteOffset": 0 } ], "md5sum": "edde67e4b7d45c1b7d56b75ee2de3088" }, { "dataPath": "params_shard_448.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.77.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "4dceacfd05ab66a0957e2b5ff2f5b487" }, { "dataPath": "params_shard_449.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.77.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "dfd3b2fb6fa58c97062352e320bbb410" }, { "dataPath": "params_shard_450.bin", "format": "raw-shard", "nbytes": 93978624, "records": [ { "name": "model.layers.78.mlp.down_proj.q_weight", "shape": [ 8192, 2868 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 93978624, "byteOffset": 0 } ], "md5sum": "26e15707f2a1a62436b65aaa1440fc1b" }, { "dataPath": "params_shard_451.bin", "format": "raw-shard", "nbytes": 31100928, "records": [ { "name": "model.layers.76.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.76.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11747328 }, { "name": "model.layers.77.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 11763712 }, { "name": "model.layers.77.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 11780096 }, { "name": "model.layers.77.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 23527424 }, { "name": "model.layers.77.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 23543808 }, { "name": "model.layers.77.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 27742208 } ], "md5sum": "6181ecb751235ee96894c279856ed024" }, { "dataPath": "params_shard_452.bin", "format": "raw-shard", "nbytes": 33587200, "records": [ { "name": "model.layers.78.self_attn.qkv_proj.q_weight", "shape": [ 10240, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 33587200, "byteOffset": 0 } ], "md5sum": "8b01a9d49ea5849c6c347843512845e3" }, { "dataPath": "params_shard_453.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.78.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "68347252bd94011bf38374dde220b720" }, { "dataPath": "params_shard_454.bin", "format": "raw-shard", "nbytes": 19304448, "records": [ { "name": "model.layers.78.mlp.down_proj.q_scale", "shape": [ 8192, 717 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 11747328, "byteOffset": 0 }, { "name": "model.layers.78.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 11747328 }, { "name": "model.layers.78.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 15945728 } ], "md5sum": "9716d55fa609e6f60cc57f2e9f6ef526" } ] }