diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..cf37a74ebcd20635aa7dad1df27778c22dde0a3c --- /dev/null +++ b/README.md @@ -0,0 +1,2 @@ +## MLC-LLM 模型 + diff --git a/mlc-chat-config.json b/mlc-chat-config.json new file mode 100644 index 0000000000000000000000000000000000000000..54165bf3e60f1e6c586124e49c8930298077a178 --- /dev/null +++ b/mlc-chat-config.json @@ -0,0 +1,17 @@ +{ + "model_lib": "RWKV-4-World-3B-q4f16_1", + "local_id": "RWKV-4-World-3B-q4f16_1", + "conv_template": "rwkv_world", + "temperature": 1.2, + "repetition_penalty": 0.996, + "top_p": 0.6, + "mean_gen_len": 128, + "max_gen_len": 512, + "max_window_size": 1024, + "num_shards": 1, + "shift_fill_factor": 0.3, + "tokenizer_files": [], + "model_category": "rwkv_world", + "model_name": "RWKV-4-World-3B", + "vocab_size": 65536 +} \ No newline at end of file diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..ac4eb6fe41944eefab284d5e7124bc7a4380885e --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,8896 @@ +{ + "metadata": { + "ParamSize": 808 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 83886080, + "records": [ + { + "name": "param_0", + "shape": [ + 65536, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 83886080, + "byteOffset": 0 + } + ] + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 25308160, + "records": [ + { + "name": "param_1", + "shape": [ + 65536, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 10485760, + "byteOffset": 0 + }, + { + "name": "param_2", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10485760 + }, + { + "name": "param_3", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10490880 + }, + { + "name": "param_4", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10496000 + }, + { + "name": "param_5", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10501120 + }, + { + "name": "param_6", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10506240 + }, + { + "name": "param_7", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10511360 + }, + { + "name": "param_8", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 10516480 + }, + { + "name": "param_9", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 10526720 + }, + { + "name": "param_10", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10536960 + }, + { + "name": "param_11", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10542080 + }, + { + "name": "param_12", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 10547200 + }, + { + "name": "param_13", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 10552320 + }, + { + "name": "param_14", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 13829120 + }, + { + "name": "param_15", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14238720 + }, + { + "name": "param_16", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 17515520 + }, + { + "name": "param_17", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 17925120 + }, + { + "name": "param_18", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21201920 + }, + { + "name": "param_19", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 21611520 + }, + { + "name": "param_20", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 24888320 + }, + { + "name": "param_21", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 25297920 + }, + { + "name": "param_22", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 25303040 + } + ] + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_23", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_24", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_25", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_26", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_27", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_28", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_29", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_30", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_31", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_32", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_33", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_34", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_35", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_36", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_37", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_38", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_39", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_40", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_41", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_42", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_43", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_44", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_45", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_46", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_47", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_48", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_49", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_50", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_51", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_52", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_53", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_54", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_55", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_56", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_57", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_58", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_59", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_60", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_61", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_62", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_63", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_64", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_65", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_66", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_67", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_68", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_69", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_70", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_71", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_72", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_73", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_74", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_75", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_76", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_77", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_78", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_79", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_80", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_81", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_82", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_83", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_84", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_85", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_86", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_87", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_88", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_89", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_90", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_91", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_92", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_93", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_94", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_95", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_96", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_97", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_98", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_99", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_100", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_101", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_102", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_103", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_104", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_105", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_106", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_107", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_108", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_109", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_110", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_111", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_112", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_113", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_114", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_115", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_116", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_117", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_118", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_119", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_120", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_121", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_122", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_123", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_124", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_125", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_126", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_127", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_128", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_129", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_130", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_131", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_132", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_133", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_134", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_135", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_136", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_137", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_138", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_139", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_140", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_141", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_142", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_143", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_144", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_145", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_146", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_147", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_148", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_149", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_150", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_151", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_152", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_153", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_154", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_155", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_156", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_157", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_158", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_159", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_160", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_161", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_162", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_163", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_164", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_165", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_166", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_167", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_168", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_169", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_170", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_171", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_172", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_173", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_174", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_175", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_176", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_177", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_178", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_179", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_180", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_181", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_182", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_183", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_184", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_185", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_186", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_187", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_188", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_189", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_190", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_191", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_192", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_193", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_194", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_195", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_196", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_197", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_198", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_199", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_200", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_201", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_202", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_203", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_204", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_205", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_206", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_207", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_208", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_209", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_210", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_211", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_212", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_213", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_214", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_215", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_216", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_217", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_218", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_219", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_220", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_221", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_222", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_223", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_224", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_225", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_226", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_227", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_228", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_229", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_230", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_231", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_232", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_233", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_234", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_235", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_236", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_237", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_238", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_239", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_240", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_241", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_242", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_243", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_244", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_245", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_246", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_247", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_248", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_249", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_250", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_251", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_252", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_253", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_254", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_255", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_256", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_257", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_258", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_259", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_260", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_261", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_262", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_263", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_264", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_265", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_266", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_267", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_268", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_269", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_270", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_271", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_272", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_273", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_274", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_275", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_276", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_277", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_278", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_279", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_280", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_281", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_282", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_283", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_284", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_285", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_286", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_287", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_288", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_289", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_290", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_291", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_292", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_293", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_294", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_295", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_296", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_297", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_298", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_299", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_300", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_301", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_302", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_303", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_304", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_305", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_306", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_307", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_308", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_309", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_310", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_311", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_312", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_313", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_314", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_315", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_316", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_317", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_318", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_319", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_320", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_321", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_322", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_323", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_324", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_325", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_326", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_327", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_328", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_329", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_330", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_331", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_332", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_333", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_334", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_335", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_336", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_337", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_338", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_339", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_340", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_341", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_342", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_343", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_344", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_345", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_346", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_347", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_348", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_349", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_350", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_351", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_352", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_353", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_354", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_355", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_356", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_357", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_358", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_359", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_360", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_361", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_362", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_363", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_364", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_365", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_366", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_367", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_368", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_369", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_370", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_371", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_372", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_373", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_374", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_375", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_376", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_377", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_378", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_379", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_380", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_381", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_382", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_383", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_384", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_385", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_386", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_387", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_388", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_389", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_390", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_391", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_392", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_393", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_394", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_395", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_396", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_397", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_398", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_399", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_400", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_401", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_402", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_403", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_404", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_405", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_406", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_407", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_408", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_409", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_410", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_411", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_412", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_413", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_414", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_415", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_416", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_417", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_418", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_419", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_420", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_421", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_422", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_423", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_424", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_425", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_426", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_427", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_428", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_429", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_430", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_431", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_432", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_433", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_434", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_435", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_436", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_437", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_438", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_439", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_440", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_441", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_442", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_443", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_444", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_445", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_446", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_447", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_448", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_449", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_450", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_451", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_452", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_453", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_454", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_455", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_456", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_457", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_458", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_459", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_460", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_461", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_462", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_463", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_464", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_465", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_466", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_467", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_468", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_469", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_470", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_471", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_472", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_473", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_474", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_475", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_476", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_477", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_478", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_479", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_480", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_481", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_482", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_483", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_484", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_485", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_486", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_487", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_488", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_489", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_490", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_491", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_492", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_493", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_494", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_495", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_496", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_497", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_498", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_499", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_500", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_501", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_502", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_503", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_504", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_505", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_506", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_507", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_508", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_509", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_510", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_511", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_512", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_513", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_514", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_515", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_516", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_517", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_518", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_519", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_520", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_521", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_522", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_523", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_524", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_525", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_526", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_527", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_528", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_529", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_530", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_531", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_532", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_533", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_534", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_535", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_536", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_537", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_538", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_539", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_540", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_541", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_542", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_543", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_544", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_545", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_546", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_547", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_548", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_549", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_550", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_551", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_552", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_553", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_554", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_555", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_556", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_557", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_558", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_559", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_560", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_561", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_562", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_563", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_564", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_565", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_566", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_567", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_568", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_569", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_570", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_571", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_572", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_573", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_574", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_575", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_576", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_577", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_578", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_579", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_580", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_581", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_582", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_583", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_584", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_585", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_586", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_587", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_588", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_589", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_590", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_591", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_592", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_593", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_594", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_595", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_596", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_597", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_598", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_599", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_600", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_601", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_602", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_603", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_604", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_605", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_606", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_607", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_608", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_609", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_610", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_611", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_612", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_613", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_614", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_615", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_616", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_617", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_618", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_619", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_620", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_621", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_622", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_623", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_624", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_625", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_626", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_627", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_628", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_629", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_630", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_631", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_632", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_633", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_634", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_635", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_636", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_637", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_638", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_639", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_640", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_641", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_642", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_643", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_644", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_645", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_646", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_647", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_648", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_649", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_650", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_651", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_652", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_653", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_654", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_655", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_656", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_657", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_658", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_659", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_660", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_661", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_662", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_663", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_664", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_665", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_666", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_667", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_668", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_669", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_670", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_671", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_672", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_673", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_674", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_675", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_676", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_677", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_678", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_679", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_680", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_681", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_682", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_683", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_684", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_685", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_686", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_687", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_688", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_689", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_690", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_691", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_692", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_693", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_694", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_695", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_696", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_697", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_698", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_699", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_700", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_701", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_702", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_703", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_704", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_705", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_706", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_707", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_708", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_709", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_710", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_711", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_712", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_713", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_714", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_715", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_716", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_717", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_718", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_719", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_720", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_721", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_722", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_723", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_724", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_725", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_726", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_727", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_728", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_729", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_730", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_731", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_732", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_733", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_734", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_735", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_736", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_737", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_738", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_739", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_740", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_741", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_742", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_743", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_744", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_745", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_746", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_747", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_748", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_749", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_750", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_751", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 29557760, + "records": [ + { + "name": "param_752", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_753", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_754", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_755", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_756", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14755840 + }, + { + "name": "param_757", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14760960 + }, + { + "name": "param_758", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14766080 + }, + { + "name": "param_759", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 14776320 + }, + { + "name": "param_760", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14786560 + }, + { + "name": "param_761", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14791680 + }, + { + "name": "param_762", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14796800 + }, + { + "name": "param_763", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14801920 + }, + { + "name": "param_764", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18078720 + }, + { + "name": "param_765", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 18488320 + }, + { + "name": "param_766", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 21765120 + }, + { + "name": "param_767", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 22174720 + }, + { + "name": "param_768", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 25451520 + }, + { + "name": "param_769", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 25861120 + }, + { + "name": "param_770", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 29137920 + }, + { + "name": "param_771", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29547520 + }, + { + "name": "param_772", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 29552640 + } + ] + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 33233920, + "records": [ + { + "name": "param_773", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_774", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_775", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 14745600 + }, + { + "name": "param_776", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 18022400 + }, + { + "name": "param_777", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 18432000 + }, + { + "name": "param_778", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 31539200 + }, + { + "name": "param_779", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33177600 + }, + { + "name": "param_780", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33182720 + }, + { + "name": "param_781", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33187840 + }, + { + "name": "param_782", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33192960 + }, + { + "name": "param_783", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33198080 + }, + { + "name": "param_784", + "shape": [ + 2560 + ], + "dtype": "float32", + "format": "raw", + "nbytes": 10240, + "byteOffset": 33208320 + }, + { + "name": "param_785", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33218560 + }, + { + "name": "param_786", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33223680 + }, + { + "name": "param_787", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 33228800 + } + ] + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 33187840, + "records": [ + { + "name": "param_788", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 0 + }, + { + "name": "param_789", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 3276800 + }, + { + "name": "param_790", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 3686400 + }, + { + "name": "param_791", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 6963200 + }, + { + "name": "param_792", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 7372800 + }, + { + "name": "param_793", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 10649600 + }, + { + "name": "param_794", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 11059200 + }, + { + "name": "param_795", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 14336000 + }, + { + "name": "param_796", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_797", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_798", + "shape": [ + 10240, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 14755840 + }, + { + "name": "param_799", + "shape": [ + 10240, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 27863040 + }, + { + "name": "param_800", + "shape": [ + 2560, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 3276800, + "byteOffset": 29501440 + }, + { + "name": "param_801", + "shape": [ + 2560, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 409600, + "byteOffset": 32778240 + } + ] + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 83886080, + "records": [ + { + "name": "param_806", + "shape": [ + 65536, + 320 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 83886080, + "byteOffset": 0 + } + ] + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 25241600, + "records": [ + { + "name": "param_802", + "shape": [ + 2560, + 1280 + ], + "dtype": "uint32", + "format": "raw", + "nbytes": 13107200, + "byteOffset": 0 + }, + { + "name": "param_803", + "shape": [ + 2560, + 320 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 1638400, + "byteOffset": 13107200 + }, + { + "name": "param_804", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14745600 + }, + { + "name": "param_805", + "shape": [ + 2560 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 5120, + "byteOffset": 14750720 + }, + { + "name": "param_807", + "shape": [ + 65536, + 80 + ], + "dtype": "float16", + "format": "raw", + "nbytes": 10485760, + "byteOffset": 14755840 + } + ] + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..80b6018ebb8a107faf8cd3eaa9ef4b4e77113d94 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173c77fe67ce1e80eed49e0a3f421710f905c5e0715e8aa55bd945c08d20047a +size 83886080 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea5abf8d9f5a0127cf1419d91a25334541a425b6 --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daafb6c7897c6f3b9821e57108d742773edd6ee892d97e678432501411b6d095 +size 25308160 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..76a239bcfc621b9fa523b234b812d15a8377473e --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2713993d1fd051050dd3e441e43a09385a4df76d40e2d121e0f226a4fe94b6bc +size 29557760 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..2cf65f4ecca489147e42bbfc032724f467366b4e --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffddccb0e91d65f7e72889fc5dc7e014062d7b3fae3f117dfce2c87394be6562 +size 33233920 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..656c5ebe61f28c3d67548caf1e71064c61c13d2e --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15f6fd13b7851620889ac2371381a08e2d93037f15ce66153d0d4423f663283 +size 33187840 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..c33ad859085c945e9457a627954a9f2456b9d0fc --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a793d9ef6a2c193e026c017d88c8eb77d0b0bdeef3db37e4e1ab4e8ba9f583 +size 29557760 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..84a1b79da7f06b1e96669694c22c4e837b064825 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582b32e98ce32009ae7d7b630cc917e250533d643a5b70763f0ce8e0a5ae3eca +size 33233920 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0762ff0f690458ef7bb031d3111aa5f99fcd771 --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3081bf3467751c92fb5d8f6e96979508058426cb0749a933b7dd5a4893b212ea +size 33187840 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..f91ab4831207c0baa4f30f353e03340e72f389be --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c845aefc5f25b669a5c0faa881ba2b8e2c337d2723d899d15c19eacc580dd8b +size 29557760 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..e2f3ad64680e4bbcd2823d614df2f818f7749f90 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60ec7d6403b208c685ca2678cd82f60c6cf000207657242fec35f72ff4ee86a7 +size 33233920 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..9fd00e42470f20fd18ec3afd758f3daf74ca4e32 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0867f8254de93221935f21e84f27389739ae3259263726398e191bcb25eadc +size 33187840 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..016b467ec9786db5ef75c7421be67044d33da560 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4688160648b514546b4cf354b8ff1af7fdfd9bbb1111dc3a5b5ffc05b081eb +size 29557760 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..808ad6f1365c66f438b63cd8d77175bb7889602f --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14996ebeac3720f64bfee636bdb82014851b6638d86254904addfd2eb05d5025 +size 33233920 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..1112b4e10895ad04ffa7fa3b9f7add20493adbf7 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7949ee30f1f20699ed8629a767295e0b2ead742b0cb97da201f083112c38d36 +size 33233920 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecf0f3b35213e746b66704d794f728fcfceb05bc --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1e6037e313c27b4ab88ca4e3e0613f67923142d528ace1b2670720ae10db84 +size 33187840 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..f884a18f6e03c500e8595d6fb1cddac1705c6e7c --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce42e0466b799b9e1fa8b1cd7bf92a53a28991efc1af1ee359acf738e5b884d +size 29557760 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..96c25d9f7640f5c34738ff1aa8b6afc15dbed5a7 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5b9f94a764987d9bb9dafb0c54b074a226ae9eea1d0a2d15d7176267773c3ca +size 33233920 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..d17b635a45916a8f14eb569384d4126fa5b574b1 --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:686cddb3e8d23c0c927f1b03a14ddd374f774b4b52b37f23b8f52162f6222083 +size 33187840 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..308d03d7e0587e6d9a528ac496ac937b4c3b4d52 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9505268e9d0c324a2eafbe5528547c770e28f22b5144d23371dd85d0b462377 +size 29557760 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc7214e1498c86a8a2a0e50c4ae24f5c96c61086 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0881b5c78f376e713b4a00d0e5fe831bc35bb756b1ee5e94b29bf1a4a79420 +size 33233920 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c06684704fdf39fac87ef5bd0784d46bf286868 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7e6d4e0665e64efd19d900bf5a67b267dd22d80a9aa55260efe64044558592 +size 33187840 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..91b5a8bf167aa726991709ba29862abd3bed91f7 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c80344b9b768d0bb401d7aff84968b73112a7c4a429b434cd4ff4da85fe22b +size 29557760 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ead0819b30b8056ee4a3098db75b465cf1e4157 --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef270231dd857a0ec7664dbe0f3200ffd6a17c58c3984cbf120bcdded9c351ae +size 33233920 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..98ecce3c501e8ac70e49105c3ff83f8b7e299c3b --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a190f5e5851b0b4ca11630e4c3bb3bf219caebab63fcc1139de267815ba9dd +size 33187840 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..73157a7bd99fd62163fe5e70b7ce15807f14ff4e --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d35ae6287ab47ff8f0ced47c24ec2d418ba46e9e14ac5a65e01138b877fede5 +size 33187840 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..635302516f4d687c6d7697778a7d561b8fb022a8 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1230a8d510c0d0be797efb527999983aad7294468bac35b0a9b4d84e6e771692 +size 29557760 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5a900d3b2fb1f06186aa631ef79e63700447a7b --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a23780addc8465e22330de18d55feed2e5e5d40e4cdc2218615550f2ceef45 +size 33233920 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..46e0a11b20068c6535e71e88a8f55e71393ccd26 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0f25c504a18030d1d59319c2acc9b393e61c098455aa5c02f836e3eebeb759 +size 33187840 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..7267db1f79ca4788fd34260117a8294a519bdfc0 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a23b3bb41d0a05ccdd5d9146147d0b241404324fc6442e3e2b2fac4d3a0548b +size 29557760 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..75cff2b31581d09b1a1bc1847ef0a846a49bbeaf --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac2aec5d2dd0cba268949986b65715d13b88a1a63a8de85e2bbcd2203d00d20 +size 33233920 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..9bda99094862ee1e17037d12829bdd2a9a01f233 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:650380006e127ad09dc5c7df853ed48241160e706dffd20dd7e124c278af1873 +size 33187840 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..4673e78aa9a3b8d4295dccd7a13679dbb2d41a0d --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5015a7dc1c41d8d15fe98ef4d58d3f4f943976e562a6745d41cd94b9e255b6c +size 29557760 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4d6e619123041389282436c73dea8be44bf039d --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea4b0f8f298aff7477972587bb7d3e864e0cc156b4e2a43d84eb9ba446d26044 +size 33233920 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..815180239fbfec106d7c457bd3eee56a3bab0ddb --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db8216715cae53c3d260046ea75cff964f2630cd6833d87105f3c84158a42e3f +size 33187840 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d2d7235f64c8df8f0ff5df2729d849c8db57f8a --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82a266c53467ab350784dfb145d31d7766068d37433eb190d913198c0d5fa31 +size 29557760 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef832de1cf7d91cbf07bd260fb38a066f7b3c242 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7b479769d22fcd9a874d5f6e9f9719863c4c86e7fae9f8c3cf044433d3978c +size 29557760 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..666eca1bd8cf0822d6582d760836cc3d0922bb13 --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f194d29f054f576808044ba33ddd60270dfa77854a3fcef922a1029f13db9c +size 33233920 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..0397ac16cccc46595830222e6c1b95dab111d755 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d182a0600465b0c39f52be92a0d9c2bb4d49ed46dd20a4f3b62c97c55b146e +size 33187840 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..60d42e21b7379cff5e446760ae7427bff0a88091 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac02ffe21fd1733112c3fce1ca13f2dd5a2a12cacfe68e359113f443d9ac05e5 +size 29557760 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..f8c96bbd103559b61d3b3899530cbb6695468d29 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63cc0f23fe58633d8cdb17d817e1810453d4651a89f82febc5e4915d8cb2cbf1 +size 33233920 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d21855c865032196091b5ad4029abced779a89d --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee63236386e5dcf99099c9766ebeca3c88e447fea0601727c8ba05653aa348be +size 33187840 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..ddf89b7ae300c289c65b2a364e853d1dc4dd0a1f --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdac39200f0a5f9af15c229fdb99fe07622a533ace039f5ea1ddb48b91da5ef5 +size 29557760 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2ea261bf916f00f267e795616126eb32458fd1f --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b450326ebdc0b804515ab23e8d3078ebf5c3b10f2c0624ce1acc78a205089ff0 +size 33233920 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..beb26b14a1a2ed7e009d892eb246a6b42d470a63 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9565e954c2136a6f7d34fa1f50d291d4fdbafde06663e1e7ed6e212b113ff709 +size 33187840 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..ba4cfd69264bdf483f60a061fc21f37a408947f4 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:462161b694d6543d3dced9d1e86fbda8a4cadc8c548ad14b1667b7d611ce90f8 +size 83886080 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a6650532ddeed278a23759163bbbf07e61e1f2f --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46813c4f3b1e22951bf0463a30617a018b5efbf583993b5f8fba2e8fefd031bb +size 33233920 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..f00b4fc38bf7b903329382814f813eb62b9ddf2f --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aedb871153b7bb4afe3283698ccb44cd75958da917bb75af2b553adc3b496b4f +size 25241600 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..87caed762fef610d4de298cbf2c7da26cc521d05 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bbe982a36e74b91702392643bc9c415ffe131b2d50d18db41bca554f301f085 +size 33187840 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..96c7e9743ba74428897c6795cb6ae2995b2338e6 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9e53fcb2814daa92e94d5b04aec68b2767df9e50304c4c090f6d3a758df1dc +size 29557760 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..68af8752a878e8138d42227c620f7170f5001150 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c316d59375d312d6d5437edb66cefef783f5d21d48e1be301f6cb34f04cdb876 +size 33233920 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..b8786d72121d233221cbd0c95123b6e594099b18 --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137f15eb4bfe7afa1a4ac0f89db7e8a40ff152d27435d4a9da6c9d2e9e3ff142 +size 33187840 diff --git a/tokenizer_model b/tokenizer_model new file mode 100644 index 0000000000000000000000000000000000000000..8a607ac2fd88ff6fa236e0ae58a5477b1a6c6dd3 Binary files /dev/null and b/tokenizer_model differ