{ "metadata": { "ParamSize": 485, "ParamBytes": 15201289216.0, "BitsPerParam": 3.6039124214610974 }, "records": [ { "dataPath": "params_shard_0.bin", "format": "raw-shard", "nbytes": 104960000, "records": [ { "name": "lm_head.q_weight", "shape": [ 32000, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 104960000, "byteOffset": 0 } ], "md5sum": "eb9ff5efb0810f7716e308a43a8f41eb" }, { "dataPath": "params_shard_1.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.41.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "dbd9056a69c31cf1921911b028d7e44e" }, { "dataPath": "params_shard_2.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.42.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "a067fefd7633dd460573dde9b9623e36" }, { "dataPath": "params_shard_3.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "bad01b16f54597543f00788a5766982c" }, { "dataPath": "params_shard_4.bin", "format": "raw-shard", "nbytes": 18053120, "records": [ { "name": "model.layers.42.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 0 } ], "md5sum": "56897560b086434ace6a0358715af81d" }, { "dataPath": "params_shard_5.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": "ffe19e508e9970c05640fbc767c2ec29" }, { "dataPath": "params_shard_6.bin", "format": "raw-shard", "nbytes": 31240704, "records": [ { "name": "lm_head.q_scale", "shape": [ 32000, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 13120000, "byteOffset": 0 }, { "name": "model.layers.41.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 13120000 }, { "name": "model.layers.41.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 13136384 }, { "name": "model.layers.41.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22163968 }, { "name": "model.layers.42.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 22180352 }, { "name": "model.layers.42.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 22196736 }, { "name": "model.layers.42.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 31224320 } ], "md5sum": "a577b5e9c3a4b63fac7b609cf1e6bc7f" }, { "dataPath": "params_shard_7.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.42.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.42.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "ffcaf0049fb67bf5c84cbc72ebb11339" }, { "dataPath": "params_shard_8.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.43.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "7895f0d754e205514557b0b54804167e" }, { "dataPath": "params_shard_9.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.43.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "de6dca3b9a903afc719284f3b965df73" }, { "dataPath": "params_shard_10.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": "2e9ae899e8e5837878dcc920ba85a6af" }, { "dataPath": "params_shard_11.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.42.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.43.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.43.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.43.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.43.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "3d2bf78adbe9d63020834e7f868c34e9" }, { "dataPath": "params_shard_12.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": "b39f76768d3e6b70d0ad0f92fa5dc992" }, { "dataPath": "params_shard_13.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.44.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "7bfdc36c6d67870487b3cb68192b2ff4" }, { "dataPath": "params_shard_14.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.44.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "5b5ef76d39a439feb3347ebd8e74c878" }, { "dataPath": "params_shard_15.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": "706a1bc536fdfc5455e86942afbab61c" }, { "dataPath": "params_shard_16.bin", "format": "raw-shard", "nbytes": 30472192, "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.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.44.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.44.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.44.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "c82b119a03f89bf7931a2db398639164" }, { "dataPath": "params_shard_17.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.44.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.44.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "efa351e60c35faa47d75abc8ebe72804" }, { "dataPath": "params_shard_18.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.45.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "893c75be112dfa0d47fb153c8b690e0a" }, { "dataPath": "params_shard_19.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.45.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "656ec8ba47ad4e4144835fde45326aec" }, { "dataPath": "params_shard_20.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": "b71faef27cc091c4cb06f6ff1ba4a084" }, { "dataPath": "params_shard_21.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.44.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.45.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.45.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.45.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.45.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "d79dad95f412f4d9769c9bab7e2a373a" }, { "dataPath": "params_shard_22.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.45.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.45.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "e5fbf63ce3a6b3e849da197dddbad737" }, { "dataPath": "params_shard_23.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.46.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "3327727c5178277fd38be43a202e2fad" }, { "dataPath": "params_shard_24.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.46.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "893cb30b59af6bab4f22fa0453b874d0" }, { "dataPath": "params_shard_25.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": "9babe8369445ff725705ffada641ce11" }, { "dataPath": "params_shard_26.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.45.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.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.46.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.46.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "93b2beafa7adc72e298666bfac1f7eb2" }, { "dataPath": "params_shard_27.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": "f50f7822b0ee397987b1a1c3c1302b9a" }, { "dataPath": "params_shard_28.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.47.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "3322ad875f75f44113fa687c19102ebf" }, { "dataPath": "params_shard_29.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.47.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "f7f41401ec70da43c49ea400b236ecbd" }, { "dataPath": "params_shard_30.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": "9e6523e3326908b5d6cf255ef5b61abc" }, { "dataPath": "params_shard_31.bin", "format": "raw-shard", "nbytes": 30472192, "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.47.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.47.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.47.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.47.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "6e964babe1b6f62989e66d4ab0298146" }, { "dataPath": "params_shard_32.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.47.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.47.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "2d5480fd45b4c958c2615f9b0e5b8579" }, { "dataPath": "params_shard_33.bin", "format": "raw-shard", "nbytes": 104960000, "records": [ { "name": "model.embed_tokens.q_weight", "shape": [ 32000, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 104960000, "byteOffset": 0 } ], "md5sum": "b1105158f85ca5b996876dcebf39ca30" }, { "dataPath": "params_shard_34.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.0.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "5bec64324f214f821faaa221ea4bfa9d" }, { "dataPath": "params_shard_35.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "7a9fa82095de2c4b5b9a72331dafce3d" }, { "dataPath": "params_shard_36.bin", "format": "raw-shard", "nbytes": 18053120, "records": [ { "name": "model.layers.0.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 0 } ], "md5sum": "11bb35bb40fad8732e9153a3a9ccc86b" }, { "dataPath": "params_shard_37.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": "61463bc88855bd8226627eae8d9dd452" }, { "dataPath": "params_shard_38.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.0.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "7d70b6cd8e6b42517971f8bd8f6d85b7" }, { "dataPath": "params_shard_39.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.1.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "50b7caf99b4226f4caf8cd2af5c5d2c2" }, { "dataPath": "params_shard_40.bin", "format": "raw-shard", "nbytes": 33128960, "records": [ { "name": "model.layers.47.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.norm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.embed_tokens.q_scale", "shape": [ 32000, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 13120000, "byteOffset": 3375104 }, { "name": "model.layers.0.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 16495104 }, { "name": "model.layers.0.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 16511488 }, { "name": "model.layers.0.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25539072 }, { "name": "model.layers.0.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 25555456 }, { "name": "model.layers.0.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 29753856 }, { "name": "model.layers.1.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 33112576 } ], "md5sum": "b1451e4e2c58b01b5bc7e9ff175f5a2c" }, { "dataPath": "params_shard_41.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.1.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "5540e63d4d16102e3df7a1ba93bdd4b5" }, { "dataPath": "params_shard_42.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": "a18c99b050aafc7ded4ed7d379935de2" }, { "dataPath": "params_shard_43.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": "8a3b89a8b4d9a229b85af5c3b895c412" }, { "dataPath": "params_shard_44.bin", "format": "raw-shard", "nbytes": 31295488, "records": [ { "name": "model.layers.1.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.1.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 9027584 }, { "name": "model.layers.1.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27080704 }, { "name": "model.layers.1.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 27097088 } ], "md5sum": "fce0a8574648df810a5b74cdc1d65c6d" }, { "dataPath": "params_shard_45.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.2.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "32d251d8e52438a5ed255a9dd1e309b4" }, { "dataPath": "params_shard_46.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.2.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "84cd2113fdd7a1b33f230e96e64767df" }, { "dataPath": "params_shard_47.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": "4c245c11fe5c6d40e63365603fb8aea8" }, { "dataPath": "params_shard_48.bin", "format": "raw-shard", "nbytes": 30472192, "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.2.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.2.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.2.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.2.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "6dbf526ee69d5b741d9787e95ac3b15b" }, { "dataPath": "params_shard_49.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.2.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.2.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "74ef14b60a74fadf12194673f0dd30cd" }, { "dataPath": "params_shard_50.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.3.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "f7d7fc6f627d429c6618ccdfe3d4d6ef" }, { "dataPath": "params_shard_51.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.3.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "6e97f6625f9db1ffe6d49534ec1ae95c" }, { "dataPath": "params_shard_52.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": "b48f8e3ca4fd05f5558bd36af28504dd" }, { "dataPath": "params_shard_53.bin", "format": "raw-shard", "nbytes": 30472192, "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, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.3.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.3.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "9d52e9cc07da88c100ec1df3d72c7d53" }, { "dataPath": "params_shard_54.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.3.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.3.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "568bbd28c6111311e29d18bacd85ba94" }, { "dataPath": "params_shard_55.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.4.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "404e6d3d2c94f668d4b1779f8263bb09" }, { "dataPath": "params_shard_56.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.4.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "9cc6353c475aebd23acee8838f1febdf" }, { "dataPath": "params_shard_57.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": "793788914908d12ec2fec9d55b33e20a" }, { "dataPath": "params_shard_58.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.3.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.4.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.4.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.4.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.4.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "dd8d111394c4b0a5d7263b55a0de9312" }, { "dataPath": "params_shard_59.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.4.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.4.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "66428b4bf76120c19d16420fbd3d7dc2" }, { "dataPath": "params_shard_60.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.5.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "c0b784aa36e660d6bfe0ae5da41093cd" }, { "dataPath": "params_shard_61.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.5.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "0d03bd4b8965bbc07cf4ea204803d918" }, { "dataPath": "params_shard_62.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": "53a16376dfbf32cc8ccbc063895662a8" }, { "dataPath": "params_shard_63.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.4.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.5.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.5.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.5.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.5.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "6ac2293115c3cfc0b09c47cd4c1fed40" }, { "dataPath": "params_shard_64.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.5.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.5.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "80af5999f40df48cbcdae3941deb7203" }, { "dataPath": "params_shard_65.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.6.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "13a2660d914c9d9bf2b273b96409f3f3" }, { "dataPath": "params_shard_66.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": "e0eaa1047f49871ea6041788ec78145d" }, { "dataPath": "params_shard_67.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": "f57777b070baf9d1615d11f586e2e6e5" }, { "dataPath": "params_shard_68.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.10.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "fcb9b4324cac6f48fec3191157fb682c" }, { "dataPath": "params_shard_69.bin", "format": "raw-shard", "nbytes": 28985344, "records": [ { "name": "model.layers.5.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.6.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 3358720 }, { "name": "model.layers.6.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 21411840 }, { "name": "model.layers.6.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 25610240 }, { "name": "model.layers.10.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28968960 } ], "md5sum": "6b23b3cf8edb3e20ff45af13e9dd71d2" }, { "dataPath": "params_shard_70.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.10.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "84a438218e6bc31d2383aac8fc2290a5" }, { "dataPath": "params_shard_71.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": "ca8e11528b25a8cf18e9d41224c27933" }, { "dataPath": "params_shard_72.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": "78385b0d61a934f7f45516282ddb1b89" }, { "dataPath": "params_shard_73.bin", "format": "raw-shard", "nbytes": 31295488, "records": [ { "name": "model.layers.10.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.10.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 9027584 }, { "name": "model.layers.10.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27080704 }, { "name": "model.layers.10.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 27097088 } ], "md5sum": "dcd270cdb7558a18f1dac124a4ec8f2a" }, { "dataPath": "params_shard_74.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.11.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "2c8f215af748f1764474b691bcf51178" }, { "dataPath": "params_shard_75.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.11.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "bb90a592a6be1a63cd20fb3218343a84" }, { "dataPath": "params_shard_76.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": "275e290229579269011fbbfdaf0716a9" }, { "dataPath": "params_shard_77.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.10.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.11.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.11.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.11.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.11.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "253ea5e96ebf727933318d67c7e4679d" }, { "dataPath": "params_shard_78.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": "08211aa362622c41e994bca1a9d49489" }, { "dataPath": "params_shard_79.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.12.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "ce0362f947559d6b633cf6e44c17e786" }, { "dataPath": "params_shard_80.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.12.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "8b63a574f813643ecb98a902623c3652" }, { "dataPath": "params_shard_81.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": "4e1af9a7c34b7e3b078347e853e91b98" }, { "dataPath": "params_shard_82.bin", "format": "raw-shard", "nbytes": 30472192, "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.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.12.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.12.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.12.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "14772924313e25a3de99362f1a6d49ab" }, { "dataPath": "params_shard_83.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.12.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.12.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "0aa53dd4a1e3e6802f4e1418c407dd70" }, { "dataPath": "params_shard_84.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.13.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "b1e96ebcc41aef01c47c90d566a7ffd9" }, { "dataPath": "params_shard_85.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": "4bbfa960aef4fc702226837957cde178" }, { "dataPath": "params_shard_86.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": "6716bd0533d1d597fa0e102cebde0fc3" }, { "dataPath": "params_shard_87.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.6.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "f7adeb7a9b2bf3af6550fc67bdee4d02" }, { "dataPath": "params_shard_88.bin", "format": "raw-shard", "nbytes": 28985344, "records": [ { "name": "model.layers.12.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.13.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 3358720 }, { "name": "model.layers.13.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 21411840 }, { "name": "model.layers.13.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 25610240 }, { "name": "model.layers.6.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28968960 } ], "md5sum": "5c26b62110c485d6063ac9a7b42dbd3b" }, { "dataPath": "params_shard_89.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.7.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "eb8b0ea22cbd7351b983d2fc6a830865" }, { "dataPath": "params_shard_90.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "47ad294de9e5f93cc94f2185c67a25d3" }, { "dataPath": "params_shard_91.bin", "format": "raw-shard", "nbytes": 18053120, "records": [ { "name": "model.layers.7.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 0 } ], "md5sum": "41c34bcc69a5ff6911c26c35229754ef" }, { "dataPath": "params_shard_92.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": "642416bff78b98c884fe49e4aaea7da2" }, { "dataPath": "params_shard_93.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": "66901e2f8d7b0c5a533b30af8351603d" }, { "dataPath": "params_shard_94.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.8.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "75fbeaf567e75844754b61a750b6fb53" }, { "dataPath": "params_shard_95.bin", "format": "raw-shard", "nbytes": 25677824, "records": [ { "name": "model.layers.6.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.6.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9027584 }, { "name": "model.layers.7.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9043968 }, { "name": "model.layers.7.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 9060352 }, { "name": "model.layers.7.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18087936 }, { "name": "model.layers.7.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 18104320 }, { "name": "model.layers.7.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 22302720 }, { "name": "model.layers.8.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25661440 } ], "md5sum": "2b1b6e4396c48b68ce4455b4aa50c4e1" }, { "dataPath": "params_shard_96.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.8.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "f6b9a180c338851db8ce1aab7ee2836c" }, { "dataPath": "params_shard_97.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": "69773180f3361f3b9294d7833055116c" }, { "dataPath": "params_shard_98.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.8.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "9599cbb0d2ec5ae5ab893bbde3221d34" }, { "dataPath": "params_shard_99.bin", "format": "raw-shard", "nbytes": 31295488, "records": [ { "name": "model.layers.8.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.8.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 9027584 }, { "name": "model.layers.8.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27080704 }, { "name": "model.layers.8.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 27097088 } ], "md5sum": "ba67e3d3f20f55236ec866251a375846" }, { "dataPath": "params_shard_100.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.9.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "e8ba8fdf1900f93304bd5987259c640d" }, { "dataPath": "params_shard_101.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.9.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "1603b2bdf037433ff4652388ccbcc92c" }, { "dataPath": "params_shard_102.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": "dfe4123e527dd4792b676ade25dc530e" }, { "dataPath": "params_shard_103.bin", "format": "raw-shard", "nbytes": 30472192, "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.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.9.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.9.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.9.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "56004e151402848d0bbacedca1663eed" }, { "dataPath": "params_shard_104.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.9.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.9.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "cba9f4dcb14f3c9e453a4d4174f59b19" }, { "dataPath": "params_shard_105.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.13.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "bb34da9cd3c60fb399731b70c815e2b8" }, { "dataPath": "params_shard_106.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.14.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "12e18e19782efc2e4bdd4b3f96838306" }, { "dataPath": "params_shard_107.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "e14127f97c6ff14dbd3483e85be1d608" }, { "dataPath": "params_shard_108.bin", "format": "raw-shard", "nbytes": 18053120, "records": [ { "name": "model.layers.14.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 0 } ], "md5sum": "ff9d1396308ba49e059dbfb2f00dd845" }, { "dataPath": "params_shard_109.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": "6724e45de0541e5e20d097794e3c31a9" }, { "dataPath": "params_shard_110.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": "14d24a0a827bf6b5f38141c9aeef90d2" }, { "dataPath": "params_shard_111.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.15.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "30de7b81442df5c3a296dd9eac053078" }, { "dataPath": "params_shard_112.bin", "format": "raw-shard", "nbytes": 29052928, "records": [ { "name": "model.layers.9.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.13.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.13.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.13.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12402688 }, { "name": "model.layers.14.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 12419072 }, { "name": "model.layers.14.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 12435456 }, { "name": "model.layers.14.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 21463040 }, { "name": "model.layers.14.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 21479424 }, { "name": "model.layers.14.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 25677824 }, { "name": "model.layers.15.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 29036544 } ], "md5sum": "18dce86746ffbbd29e9de47302dc6ea0" }, { "dataPath": "params_shard_113.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.15.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "dd14ca16f75ecdd548c91c123aad8334" }, { "dataPath": "params_shard_114.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": "ad06515cc8293406bd8b24434e190b8d" }, { "dataPath": "params_shard_115.bin", "format": "raw-shard", "nbytes": 26869760, "records": [ { "name": "model.layers.15.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 0 } ], "md5sum": "331e9e27c49f34d12e9db09bb83258f2" }, { "dataPath": "params_shard_116.bin", "format": "raw-shard", "nbytes": 31295488, "records": [ { "name": "model.layers.15.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.15.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 9027584 }, { "name": "model.layers.15.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27080704 }, { "name": "model.layers.15.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 27097088 } ], "md5sum": "ee34ec8611278949db6f06822aff43f7" }, { "dataPath": "params_shard_117.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.16.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "7d07a0b802282a34669415103c4a4c42" }, { "dataPath": "params_shard_118.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.16.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "278ef6be82e7651ef545ec88f3d56925" }, { "dataPath": "params_shard_119.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": "b30dd48f7c26d504d1999ecc2da41b60" }, { "dataPath": "params_shard_120.bin", "format": "raw-shard", "nbytes": 30472192, "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, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.16.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.16.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "aafdbf7dddd24588ca360c8d6e54d506" }, { "dataPath": "params_shard_121.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.16.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.16.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "1b3724cc92ea2a0082bb6bb3e55f7654" }, { "dataPath": "params_shard_122.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.17.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "bd44c10c66eec6dcd8799593e388b679" }, { "dataPath": "params_shard_123.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.17.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "3996ada8576910491cfcc19aff5094f2" }, { "dataPath": "params_shard_124.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": "a46b25e452c8ae20084b5e6f3465b383" }, { "dataPath": "params_shard_125.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.16.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.17.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.17.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.17.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.17.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "6ba3654fb85777dc4d3dc003dda6b63a" }, { "dataPath": "params_shard_126.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.17.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.17.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "287cf0b0ff892e5fae391623206aa02f" }, { "dataPath": "params_shard_127.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.18.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "31cfc1d76d2100471daa2cf1dfb8c52c" }, { "dataPath": "params_shard_128.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.18.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "e8be3e3f73df86c151148221327d11c6" }, { "dataPath": "params_shard_129.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": "6736b30c300f11e14de2cd8d7e602331" }, { "dataPath": "params_shard_130.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.17.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.18.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.18.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.18.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.18.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "beb84b8e21d8294427c6505e339539ee" }, { "dataPath": "params_shard_131.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.18.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.18.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "b9950623ae28839c6b2f8baa169ce540" }, { "dataPath": "params_shard_132.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.19.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "0ee788bba669e9ad496e4ddfc7865184" }, { "dataPath": "params_shard_133.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.19.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "d4eb7f1963f8264c3735a356cad4f16f" }, { "dataPath": "params_shard_134.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": "fb1aec402593f7d4b54b8816b0cf63a7" }, { "dataPath": "params_shard_135.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.18.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.19.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.19.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.19.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.19.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "559317f64784597f26fa20153471ebab" }, { "dataPath": "params_shard_136.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.19.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.19.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "78def11e0419acf8dc840f25d4813e5a" }, { "dataPath": "params_shard_137.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.20.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "894c908a757047359f53fd03ed6abc4e" }, { "dataPath": "params_shard_138.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": "ad90febec879c6848aa0a7aabf607a08" }, { "dataPath": "params_shard_139.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": "9849fcd7d5b2756cc7f558f109700ee8" }, { "dataPath": "params_shard_140.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.20.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "166287b83d645fb0780d27d5a8bb0b81" }, { "dataPath": "params_shard_141.bin", "format": "raw-shard", "nbytes": 28985344, "records": [ { "name": "model.layers.19.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.20.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 3358720 }, { "name": "model.layers.20.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 21411840 }, { "name": "model.layers.20.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 25610240 }, { "name": "model.layers.20.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28968960 } ], "md5sum": "3005862d779706cc3b87b373ac475d13" }, { "dataPath": "params_shard_142.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.21.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "bcbd75722e02879647eda20df28dc2dd" }, { "dataPath": "params_shard_143.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "a2d29cfe9b20d6afb4d14af761291bd0" }, { "dataPath": "params_shard_144.bin", "format": "raw-shard", "nbytes": 18053120, "records": [ { "name": "model.layers.21.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 0 } ], "md5sum": "2eae184bb9bfa2f4b6b6f7c2f48cab1f" }, { "dataPath": "params_shard_145.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": "8916f70d2d0298aab038cbe65de068d4" }, { "dataPath": "params_shard_146.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": "869912a42ba0dc128ebe829088b67de5" }, { "dataPath": "params_shard_147.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.22.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "0885ac238a764755de5797261744184b" }, { "dataPath": "params_shard_148.bin", "format": "raw-shard", "nbytes": 25677824, "records": [ { "name": "model.layers.20.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.20.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9027584 }, { "name": "model.layers.21.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9043968 }, { "name": "model.layers.21.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 9060352 }, { "name": "model.layers.21.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18087936 }, { "name": "model.layers.21.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 18104320 }, { "name": "model.layers.21.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 22302720 }, { "name": "model.layers.22.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25661440 } ], "md5sum": "ef9510911582b3d005515434ab428960" }, { "dataPath": "params_shard_149.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.22.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "51d79f52ec96b40e3b1f46cef162893d" }, { "dataPath": "params_shard_150.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": "eb4c1b5e2da231c05075dbd6fa9eced9" }, { "dataPath": "params_shard_151.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": "15ae3b3390f44b3b1dad376ceb7227f2" }, { "dataPath": "params_shard_152.bin", "format": "raw-shard", "nbytes": 31295488, "records": [ { "name": "model.layers.22.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.22.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 9027584 }, { "name": "model.layers.22.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27080704 }, { "name": "model.layers.22.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 27097088 } ], "md5sum": "b2b08a3306194faefbbd39ebd139de91" }, { "dataPath": "params_shard_153.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.23.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "522d7f32086584fe67facd877f3845bd" }, { "dataPath": "params_shard_154.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.23.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "9b52d98f16f743e6c8246e4670b37728" }, { "dataPath": "params_shard_155.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": "8b3c4aeee36eff24e08ca146b77d8d84" }, { "dataPath": "params_shard_156.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.22.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.23.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.23.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.23.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.23.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "b525b13e0b7d5bea5a51a5cbe6edb5e4" }, { "dataPath": "params_shard_157.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": "611f82095e1ad01ab0e63508fe7c69e0" }, { "dataPath": "params_shard_158.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.24.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "b786d45efa6598ca9a2912b4677eb8ae" }, { "dataPath": "params_shard_159.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.24.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "1c30a0f6a3b1dc9a0a3a1445a841e041" }, { "dataPath": "params_shard_160.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": "0da55e3a91161dd0911f0c973ca0272e" }, { "dataPath": "params_shard_161.bin", "format": "raw-shard", "nbytes": 30472192, "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, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.24.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.24.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "4c3b4760ffd7ca67c967cc88de539229" }, { "dataPath": "params_shard_162.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.24.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.24.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "27d31332dccab6cb4f7a5b2d54bb5a5b" }, { "dataPath": "params_shard_163.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.25.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "097656fd667b274ee68cdc4dae760aa0" }, { "dataPath": "params_shard_164.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.25.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "a4ca9684b237476888a838038d15cb1d" }, { "dataPath": "params_shard_165.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": "da5310be315278325b13edc220f9f1d8" }, { "dataPath": "params_shard_166.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.24.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.25.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.25.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.25.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.25.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "181970536c3e5b7e8c68218e782855cc" }, { "dataPath": "params_shard_167.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.25.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.25.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "32c010071a4d974b5d7fd53b702dc5ce" }, { "dataPath": "params_shard_168.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.26.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "8bb4cc5daa14c8f1aca952b73f00141a" }, { "dataPath": "params_shard_169.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.26.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "f1671f52986b72f40e05a0d305f04e17" }, { "dataPath": "params_shard_170.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": "6a49fb046b9e54c01816bc1eddc7a026" }, { "dataPath": "params_shard_171.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.25.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.26.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.26.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.26.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.26.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "3c418d3a8b76c0d6cce877f61ea9b9e1" }, { "dataPath": "params_shard_172.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.26.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.26.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "380ab691296450a1f6013b4cb76189dc" }, { "dataPath": "params_shard_173.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.27.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "2ea68bd3078fc30706a89ef51f879564" }, { "dataPath": "params_shard_174.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": "27945da8867273c6cb88baff193342e9" }, { "dataPath": "params_shard_175.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": "a71ef908a87e1b7fe1df15676f3db247" }, { "dataPath": "params_shard_176.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.27.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "b86681113f6182dcbcaba86023af7aad" }, { "dataPath": "params_shard_177.bin", "format": "raw-shard", "nbytes": 28985344, "records": [ { "name": "model.layers.26.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.27.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 3358720 }, { "name": "model.layers.27.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 21411840 }, { "name": "model.layers.27.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 25610240 }, { "name": "model.layers.27.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28968960 } ], "md5sum": "6a4fde8b518f67e3b4e43cfecd0a4980" }, { "dataPath": "params_shard_178.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.28.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "0a6df1d9f3c61e5124b482dcabfe71a8" }, { "dataPath": "params_shard_179.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "8f3a9c9325385f59b71330cde9efe534" }, { "dataPath": "params_shard_180.bin", "format": "raw-shard", "nbytes": 18053120, "records": [ { "name": "model.layers.28.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 0 } ], "md5sum": "b3df2f80f79db63a375717685e935ec5" }, { "dataPath": "params_shard_181.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": "7808cfa315a5529b5ddd6dc9822f1b9a" }, { "dataPath": "params_shard_182.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": "6901ea61a9050f8ecb7a2eb2db4fc333" }, { "dataPath": "params_shard_183.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.29.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "6b8e6c226ec90bb26e2083d3bf3fb4a0" }, { "dataPath": "params_shard_184.bin", "format": "raw-shard", "nbytes": 25677824, "records": [ { "name": "model.layers.27.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.27.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9027584 }, { "name": "model.layers.28.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9043968 }, { "name": "model.layers.28.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 9060352 }, { "name": "model.layers.28.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18087936 }, { "name": "model.layers.28.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 18104320 }, { "name": "model.layers.28.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 22302720 }, { "name": "model.layers.29.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25661440 } ], "md5sum": "9a5684bed30ace78fe2d5e635ec2e761" }, { "dataPath": "params_shard_185.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.29.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "7a7bf0e7a5c59b964effdb161aff4b3a" }, { "dataPath": "params_shard_186.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": "e342640fbf0a4a7d8b18090dcb88ecd5" }, { "dataPath": "params_shard_187.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": "8f758eb2bae1efb4e3bfba66e1a1eee3" }, { "dataPath": "params_shard_188.bin", "format": "raw-shard", "nbytes": 31295488, "records": [ { "name": "model.layers.29.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.29.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 9027584 }, { "name": "model.layers.29.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27080704 }, { "name": "model.layers.29.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 27097088 } ], "md5sum": "333d9267213fc3093145c78c497e3d18" }, { "dataPath": "params_shard_189.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.30.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "6d6f68dd14c37c584ae43d35cfdd844a" }, { "dataPath": "params_shard_190.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.30.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "6a9eb4f575d6bf0062639b98e112fd73" }, { "dataPath": "params_shard_191.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": "ec4d3c990b8af2e90aba35e2b9dcbbdd" }, { "dataPath": "params_shard_192.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.29.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.30.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.30.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.30.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.30.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "04ece99affec4638936741545f8f2c7a" }, { "dataPath": "params_shard_193.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.30.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.30.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "cec1a3c5df8f1bf88e1ed87b1bf93241" }, { "dataPath": "params_shard_194.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.31.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "fe64444d6cc151307feea29fa7774ab9" }, { "dataPath": "params_shard_195.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.31.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "d753360f66468b6dc5b4d6d625374c73" }, { "dataPath": "params_shard_196.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": "1ed9046d1a657ddc74bad16a553f1a89" }, { "dataPath": "params_shard_197.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.30.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.31.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.31.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.31.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.31.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "5463d022efc335fea9d75ea95984e252" }, { "dataPath": "params_shard_198.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": "0a1ef17e7d33e8b760037617bc4030d6" }, { "dataPath": "params_shard_199.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.32.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "972162b63c8785f02225e19bda244774" }, { "dataPath": "params_shard_200.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.32.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "adbaf7ad79f7d7e138840a4ee00d96e5" }, { "dataPath": "params_shard_201.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": "de5b412713d87abbb7a5e1a9a2661094" }, { "dataPath": "params_shard_202.bin", "format": "raw-shard", "nbytes": 30472192, "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, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.32.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.32.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "ea4eb75dab37cba1222f01efe3373238" }, { "dataPath": "params_shard_203.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.32.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.32.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "2e1050e4b028010e90e92f8513d248d7" }, { "dataPath": "params_shard_204.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.33.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "e06f4f21c9e3cd7d44ef1c6149b59096" }, { "dataPath": "params_shard_205.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.33.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "fa70facfeadd3793c4f80fa31affff9a" }, { "dataPath": "params_shard_206.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": "a93cf72b29b582a89e6015fd6350ddf1" }, { "dataPath": "params_shard_207.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.32.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.33.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.33.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.33.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.33.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "b20db22fb12b372fecaa83848e655227" }, { "dataPath": "params_shard_208.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.33.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.33.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "a89da0ad1d371f5780d45d22d3a15850" }, { "dataPath": "params_shard_209.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.34.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "9c203211846864e5231e3f4b49702f77" }, { "dataPath": "params_shard_210.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": "db1fe2d07a68074a5cd50b9dde3ec9c0" }, { "dataPath": "params_shard_211.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": "c7b11747986bf7468d1a87d64d191650" }, { "dataPath": "params_shard_212.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.34.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "fcc7a467cfeea6dc4489a6115ea45155" }, { "dataPath": "params_shard_213.bin", "format": "raw-shard", "nbytes": 28985344, "records": [ { "name": "model.layers.33.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.34.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 3358720 }, { "name": "model.layers.34.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 21411840 }, { "name": "model.layers.34.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 25610240 }, { "name": "model.layers.34.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 28968960 } ], "md5sum": "78c1c2888c84ef1449e6d12c7cbf9528" }, { "dataPath": "params_shard_214.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.35.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "73793ebb86b41dccb876cbce8fa72e9b" }, { "dataPath": "params_shard_215.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "4aba2f69712a418b480796d8487927ef" }, { "dataPath": "params_shard_216.bin", "format": "raw-shard", "nbytes": 18053120, "records": [ { "name": "model.layers.35.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 0 } ], "md5sum": "661ea34ca961c0d89f82b20cce6a677f" }, { "dataPath": "params_shard_217.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": "373826277fa1ea9852ba9c1c5d6dd065" }, { "dataPath": "params_shard_218.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": "126172de910cd001a370d166d3b21b27" }, { "dataPath": "params_shard_219.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.36.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "05834dddc12cd425b85ca049e53f53b7" }, { "dataPath": "params_shard_220.bin", "format": "raw-shard", "nbytes": 25677824, "records": [ { "name": "model.layers.34.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.34.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9027584 }, { "name": "model.layers.35.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 9043968 }, { "name": "model.layers.35.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 9060352 }, { "name": "model.layers.35.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 18087936 }, { "name": "model.layers.35.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 18104320 }, { "name": "model.layers.35.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 22302720 }, { "name": "model.layers.36.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 25661440 } ], "md5sum": "eaedbbf2714e045ad7bbcc4f07904470" }, { "dataPath": "params_shard_221.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.36.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "e4dba23fbb8a1fefe641ce9a939304d1" }, { "dataPath": "params_shard_222.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": "6564bbef7178e7ba0fea4ef2ffbe2cc8" }, { "dataPath": "params_shard_223.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": "bb2c37fe013a1d3cb4281c390ad4a8ef" }, { "dataPath": "params_shard_224.bin", "format": "raw-shard", "nbytes": 31295488, "records": [ { "name": "model.layers.36.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 0 }, { "name": "model.layers.36.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 9027584 }, { "name": "model.layers.36.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 27080704 }, { "name": "model.layers.36.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 27097088 } ], "md5sum": "390086b6af79562e7204ba3e6909e986" }, { "dataPath": "params_shard_225.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.37.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "69791aca2a2c254409733bbe2ffb98a2" }, { "dataPath": "params_shard_226.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.37.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "1b26c13c8379b1d13ecc988bba2e65f6" }, { "dataPath": "params_shard_227.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": "b2b572c3a03f7b56396a0f3459e76b2e" }, { "dataPath": "params_shard_228.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.36.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.37.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.37.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.37.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.37.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "a91039a1343da359471ab80e2edddf7b" }, { "dataPath": "params_shard_229.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.37.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.37.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "432ea45d77847bba09c4599d97be6c65" }, { "dataPath": "params_shard_230.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.38.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "63a29d24dfdf1173dbb6211273fd78b1" }, { "dataPath": "params_shard_231.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.38.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "2c4e15e4eb89e79062b7baf2a171616f" }, { "dataPath": "params_shard_232.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": "bb05549921a52755ca742899deadae03" }, { "dataPath": "params_shard_233.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.37.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.38.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.38.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.38.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.38.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "aa3db819989c1b3309fe91479407e4f5" }, { "dataPath": "params_shard_234.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.38.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.38.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "0f16d489c7e6eec150d96949f1f3d31f" }, { "dataPath": "params_shard_235.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.39.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "4befd7bef243c24f6a94a150f9cf7311" }, { "dataPath": "params_shard_236.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.39.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "db7f95df1080575de6d4648aabcc65af" }, { "dataPath": "params_shard_237.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": "fac3321d9c69bf33bcadcf3bae96b251" }, { "dataPath": "params_shard_238.bin", "format": "raw-shard", "nbytes": 30472192, "records": [ { "name": "model.layers.38.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.39.input_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 3358720 }, { "name": "model.layers.39.mlp.down_proj.q_scale", "shape": [ 8192, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.39.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.39.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "fbd77121fcba06643face1b47c7b67b3" }, { "dataPath": "params_shard_239.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": "113ec90883ca2574cd94009309f1a8db" }, { "dataPath": "params_shard_240.bin", "format": "raw-shard", "nbytes": 72220672, "records": [ { "name": "model.layers.40.mlp.down_proj.q_weight", "shape": [ 8192, 2204 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 72220672, "byteOffset": 0 } ], "md5sum": "56d81fffbdd22689c520b3953e42367e" }, { "dataPath": "params_shard_241.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.40.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "716ef7b4d27f359b579154971652b586" }, { "dataPath": "params_shard_242.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": "c7216fccdce37c8409687e8936f6ee37" }, { "dataPath": "params_shard_243.bin", "format": "raw-shard", "nbytes": 30472192, "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, 551 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 9027584, "byteOffset": 3375104 }, { "name": "model.layers.40.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 12402688 }, { "name": "model.layers.40.post_attention_layernorm.weight", "shape": [ 8192 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 16384, "byteOffset": 30455808 } ], "md5sum": "2077c6381f4ed6b201d13cc519ce54f9" }, { "dataPath": "params_shard_244.bin", "format": "raw-shard", "nbytes": 31068160, "records": [ { "name": "model.layers.40.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 0 }, { "name": "model.layers.40.self_attn.o_proj.q_weight", "shape": [ 8192, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 26869760, "byteOffset": 4198400 } ], "md5sum": "c2b270dc8767d4c0626b862d5a6c8230" }, { "dataPath": "params_shard_245.bin", "format": "raw-shard", "nbytes": 144424960, "records": [ { "name": "model.layers.41.mlp.gate_up_proj.q_weight", "shape": [ 44032, 820 ], "dtype": "uint32", "format": "f32-to-bf16", "nbytes": 144424960, "byteOffset": 0 } ], "md5sum": "23720bd3e2ef06662b1b4115ac520be5" }, { "dataPath": "params_shard_246.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": "aaaabada45b70ff01f6cb3975427d23a" }, { "dataPath": "params_shard_247.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": "5539a5c39a48dfa47657074160cd1511" }, { "dataPath": "params_shard_248.bin", "format": "raw-shard", "nbytes": 28968960, "records": [ { "name": "model.layers.40.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 0 }, { "name": "model.layers.41.mlp.gate_up_proj.q_scale", "shape": [ 44032, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 18053120, "byteOffset": 3358720 }, { "name": "model.layers.41.self_attn.qkv_proj.q_scale", "shape": [ 10240, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 4198400, "byteOffset": 21411840 }, { "name": "model.layers.41.self_attn.o_proj.q_scale", "shape": [ 8192, 205 ], "dtype": "float16", "format": "f32-to-bf16", "nbytes": 3358720, "byteOffset": 25610240 } ], "md5sum": "7864c17d4e12c662d04df9ee04b2f5be" } ] }