{ "tokenizer_source": "models/deberta-v3-large-mnli", "tokenizer_class": "DebertaV2Tokenizer", "vocab_size": 128000, "model_max_length": 512, "special_tokens": { "cls": "[CLS]", "sep": "[SEP]", "pad": "[PAD]", "unk": "[UNK]", "cls_id": 1, "sep_id": 2, "pad_id": 0, "unk_id": 3 }, "pairs": [ { "name": "simple_entail", "premise": "Paris is the capital of France.", "hypothesis": "France's capital is Paris.", "token_ids": [ 1, 3045, 269, 262, 1909, 265, 2378, 260, 2, 2378, 280, 268, 1909, 269, 3045, 260, 2 ], "attention_mask": [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "token_strings": [ "[CLS]", "▁Paris", "▁is", "▁the", "▁capital", "▁of", "▁France", ".", "[SEP]", "▁France", "'", "s", "▁capital", "▁is", "▁Paris", ".", "[SEP]" ] }, { "name": "simple_contradict", "premise": "The cat sat on the mat.", "hypothesis": "There was no cat anywhere.", "token_ids": [ 1, 279, 3185, 3208, 277, 262, 8358, 260, 2, 443, 284, 363, 3185, 2619, 260, 2 ], "attention_mask": [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "token_strings": [ "[CLS]", "▁The", "▁cat", "▁sat", "▁on", "▁the", "▁mat", ".", "[SEP]", "▁There", "▁was", "▁no", "▁cat", "▁anywhere", ".", "[SEP]" ] }, { "name": "neutral", "premise": "Marie Curie won the Nobel Prize in Physics in 1903.", "hypothesis": "She also worked on radioactive materials.", "token_ids": [ 1, 8013, 60560, 722, 262, 14359, 7292, 267, 11208, 267, 25008, 260, 2, 503, 327, 1103, 277, 21194, 1375, 260, 2 ], "attention_mask": [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "token_strings": [ "[CLS]", "▁Marie", "▁Curie", "▁won", "▁the", "▁Nobel", "▁Prize", "▁in", "▁Physics", "▁in", "▁1903", ".", "[SEP]", "▁She", "▁also", "▁worked", "▁on", "▁radioactive", "▁materials", ".", "[SEP]" ] }, { "name": "contraction_punct", "premise": "It's the world's biggest waterfall, isn't it?", "hypothesis": "Niagara Falls is the world's largest waterfall.", "token_ids": [ 1, 325, 280, 268, 262, 447, 280, 268, 1869, 15931, 261, 928, 280, 297, 278, 302, 2, 18722, 7167, 269, 262, 447, 280, 268, 1705, 15931, 260, 2 ], "attention_mask": [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "token_strings": [ "[CLS]", "▁It", "'", "s", "▁the", "▁world", "'", "s", "▁biggest", "▁waterfall", ",", "▁isn", "'", "t", "▁it", "?", "[SEP]", "▁Niagara", "▁Falls", "▁is", "▁the", "▁world", "'", "s", "▁largest", "▁waterfall", ".", "[SEP]" ] }, { "name": "all_upper", "premise": "THE QUICK BROWN FOX JUMPS OVER THE LAZY DOG.", "hypothesis": "A fox jumped over a dog.", "token_ids": [ 1, 1598, 60491, 49036, 17825, 84612, 430, 21720, 1598, 5240, 54368, 56180, 260, 2, 336, 16123, 6827, 360, 266, 1560, 260, 2 ], "attention_mask": [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "token_strings": [ "[CLS]", "▁THE", "▁QUICK", "▁BROWN", "▁FOX", "▁JUMP", "S", "▁OVER", "▁THE", "▁LA", "ZY", "▁DOG", ".", "[SEP]", "▁A", "▁fox", "▁jumped", "▁over", "▁a", "▁dog", ".", "[SEP]" ] }, { "name": "long_premise_short_hyp", "premise": "Deep Space 1 was launched on October 24, 1998, as the first mission of NASA's New Millennium Program. It tested twelve advanced technologies, including the Remote Agent autonomous control system, the first time an AI system had primary command of a spacecraft.", "hypothesis": "Deep Space 1 was launched in 1998.", "token_ids": [ 1, 7222, 4204, 376, 284, 2682, 277, 1370, 969, 261, 4286, 261, 283, 262, 362, 2151, 265, 7658, 280, 268, 485, 19898, 2659, 260, 325, 3457, 6883, 2171, 2737, 261, 500, 262, 12252, 8618, 12014, 719, 492, 261, 262, 362, 326, 299, 5536, 492, 330, 1862, 3282, 265, 266, 16394, 260, 2, 7222, 4204, 376, 284, 2682, 267, 4286, 260, 2 ], "attention_mask": [ 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1 ], "token_strings": [ "[CLS]", "▁Deep", "▁Space", "▁1", "▁was", "▁launched", "▁on", "▁October", "▁24", ",", "▁1998", ",", "▁as", "▁the", "▁first", "▁mission", "▁of", "▁NASA", "'", "s", "▁New", "▁Millennium", "▁Program", ".", "▁It", "▁tested", "▁twelve", "▁advanced", "▁technologies", ",", "▁including", "▁the", "▁Remote", "▁Agent", "▁autonomous", "▁control", "▁system", ",", "▁the", "▁first", "▁time", "▁an", "▁AI", "▁system", "▁had", "▁primary", "▁command", "▁of", "▁a", "▁spacecraft", ".", "[SEP]", "▁Deep", "▁Space", "▁1", "▁was", "▁launched", "▁in", "▁1998", ".", "[SEP]" ] } ] }