task_arch.json

{"text_classification": {"architectures": ["ALBERT", "BART", "BERT", "BigBird", "BigBird-Pegasus", "BioGpt", "BLOOM", "CamemBERT", "CANINE", "CodeLlama", "ConvBERT", "CTRL", "Data2VecText", "DeBERTa", "DeBERTa-v2", "DistilBERT", "ELECTRA", "ERNIE", "ErnieM", "ESM", "Falcon", "FlauBERT", "FNet", "Funnel Transformer", "GPT-Sw3", "OpenAI GPT-2", "GPTBigCode", "GPT Neo", "GPT NeoX", "GPT-J", "I-BERT", "LayoutLM", "LayoutLMv2", "LayoutLMv3", "LED", "LiLT", "LLaMA", "Longformer", "LUKE", "MarkupLM", "mBART", "MEGA", "Megatron-BERT", "Mistral", "Mixtral", "MobileBERT", "MPNet", "MPT", "MRA", "MT5", "MVP", "Nezha", "Nystr\u00f6mformer", "OpenLlama", "OpenAI GPT", "OPT", "Perceiver", "Persimmon", "Phi", "PLBart", "QDQBert", "Qwen2", "Reformer", "RemBERT", "RoBERTa", "RoBERTa-PreLayerNorm", "RoCBert", "RoFormer", "SqueezeBERT", "T5", "TAPAS", "Transformer-XL", "UMT5", "XLM", "XLM-RoBERTa", "XLM-RoBERTa-XL", "XLNet", "X-MOD", "YOSO"], "AutoModelClass": "AutoModelForSequenceClassification", "dataset": "imdb", "model_used": "distilbert-base-uncased"}, "token_classification": {"architectures": ["ALBERT", "BERT", "BigBird", "BioGpt", "BLOOM", "BROS", "CamemBERT", "CANINE", "ConvBERT", "Data2VecText", "DeBERTa", "DeBERTa-v2", "DistilBERT", "ELECTRA", "ERNIE", "ErnieM", "ESM", "Falcon", "FlauBERT", "FNet", "Funnel Transformer", "GPT-Sw3", "OpenAI GPT-2", "GPTBigCode", "GPT Neo", "GPT NeoX", "I-BERT", "LayoutLM", "LayoutLMv2", "LayoutLMv3", "LiLT", "Longformer", "LUKE", "MarkupLM", "MEGA", "Megatron-BERT", "MobileBERT", "MPNet", "MPT", "MRA", "MT5", "Nezha", "Nystr\u00f6mformer", "Phi", "QDQBert", "RemBERT", "RoBERTa", "RoBERTa-PreLayerNorm", "RoCBert", "RoFormer", "SqueezeBERT", "T5", "UMT5", "XLM", "XLM-RoBERTa", "XLM-RoBERTa-XL", "XLNet", "X-MOD", "YOSO"], "AutoModelClass": "AutoModelForTokenClassification", "dataset": "wnut_17", "model_used": "distilbert-base-uncased"}, "question_answering": {"architectures": ["ALBERT", "BART", "BERT", "BigBird", "BigBird-Pegasus", "BLOOM", "CamemBERT", "CANINE", "ConvBERT", "Data2VecText", "DeBERTa", "DeBERTa-v2", "DistilBERT", "ELECTRA", "ERNIE", "ErnieM", "Falcon", "FlauBERT", "FNet", "Funnel Transformer", "OpenAI GPT-2", "GPT Neo", "GPT NeoX", "GPT-J", "I-BERT", "LayoutLMv2", "LayoutLMv3", "LED", "LiLT", "LLaMA", "Longformer", "LUKE", "LXMERT", "MarkupLM", "mBART", "MEGA", "Megatron-BERT", "MobileBERT", "MPNet", "MPT", "MRA", "MT5", "MVP", "Nezha", "Nystr\u00f6mformer", "OPT", "QDQBert", "Reformer", "RemBERT", "RoBERTa", "RoBERTa-PreLayerNorm", "RoCBert", "RoFormer", "Splinter", "SqueezeBERT", "T5", "UMT5", "XLM", "XLM-RoBERTa", "XLM-RoBERTa-XL", "XLNet", "X-MOD", "YOSO"], "AutoModelClass": "AutoModelForQuestionAnswering", "dataset": "squad", "model_used": "distilbert-base-uncased"}, "causal_lm": {"architectures": ["BART", "BERT", "Bert Generation", "BigBird", "BigBird-Pegasus", "BioGpt", "Blenderbot", "BlenderbotSmall", "BLOOM", "CamemBERT", "CodeLlama", "CodeGen", "CPM-Ant", "CTRL", "Data2VecText", "ELECTRA", "ERNIE", "Falcon", "Fuyu", "GIT", "GPT-Sw3", "OpenAI GPT-2", "GPTBigCode", "GPT Neo", "GPT NeoX", "GPT NeoX Japanese", "GPT-J", "LLaMA", "Marian", "mBART", "MEGA", "Megatron-BERT", "Mistral", "Mixtral", "MPT", "MusicGen", "MVP", "OpenLlama", "OpenAI GPT", "OPT", "Pegasus", "Persimmon", "Phi", "PLBart", "ProphetNet", "QDQBert", "Qwen2", "Reformer", "RemBERT", "RoBERTa", "RoBERTa-PreLayerNorm", "RoCBert", "RoFormer", "RWKV", "Speech2Text2", "Transformer-XL", "TrOCR", "Whisper", "XGLM", "XLM", "XLM-ProphetNet", "XLM-RoBERTa", "XLM-RoBERTa-XL", "XLNet", "X-MOD"], "AutoModelClass": "AutoModelForCausalLM", "dataset": "eli5_category", "model_used": "distilgpt2"}, "masked_lm": {"architectures": ["ALBERT", "BART", "BERT", "BigBird", "CamemBERT", "ConvBERT", "Data2VecText", "DeBERTa", "DeBERTa-v2", "DistilBERT", "ELECTRA", "ERNIE", "ESM", "FlauBERT", "FNet", "Funnel Transformer", "I-BERT", "LayoutLM", "Longformer", "LUKE", "mBART", "MEGA", "Megatron-BERT", "MobileBERT", "MPNet", "MRA", "MVP", "Nezha", "Nystr\u00f6mformer", "Perceiver", "QDQBert", "Reformer", "RemBERT", "RoBERTa", "RoBERTa-PreLayerNorm", "RoCBert", "RoFormer", "SqueezeBERT", "TAPAS", "Wav2Vec2", "XLM", "XLM-RoBERTa", "XLM-RoBERTa-XL", "X-MOD", "YOSO"], "AutoModelClass": "AutoModelForMaskedLM", "dataset": "eli-5", "model_used": "distilroberta-base"}, "translation": {"architectures": ["BART", "BigBird-Pegasus", "Blenderbot", "BlenderbotSmall", "Encoder decoder", "FairSeq Machine-Translation", "GPTSAN-japanese", "LED", "LongT5", "M2M100", "Marian", "mBART", "MT5", "MVP", "NLLB", "NLLB-MOE", "Pegasus", "PEGASUS-X", "PLBart", "ProphetNet", "SeamlessM4T", "SeamlessM4Tv2", "SwitchTransformers", "T5", "UMT5", "XLM-ProphetNet"], "AutoModelClass": "AutoModelForSeq2SeqLM", "dataset": "opus_books", "model_used": "t5-small"}, "summarization": {"architectures": ["BART", "BigBird-Pegasus", "Blenderbot", "BlenderbotSmall", "Encoder decoder", "FairSeq Machine-Translation", "GPTSAN-japanese", "LED", "LongT5", "M2M100", "Marian", "mBART", "MT5", "MVP", "NLLB", "NLLB-MOE", "Pegasus", "PEGASUS-X", "PLBart", "ProphetNet", "SeamlessM4T", "SeamlessM4Tv2", "SwitchTransformers", "T5", "UMT5", "XLM-ProphetNet"], "AutoModelClass": "AutoModelForSeq2SeqLM", "dataset": "billsum", "model_used": "t5-small"}, "multiple_choice": {"architectures": ["ALBERT", "BERT", "BigBird", "CamemBERT", "CANINE", "ConvBERT", "Data2VecText", "DeBERTa-v2", "DistilBERT", "ELECTRA", "ERNIE", "ErnieM", "FlauBERT", "FNet", "Funnel Transformer", "I-BERT", "Longformer", "LUKE", "MEGA", "Megatron-BERT", "MobileBERT", "MPNet", "MRA", "Nezha", "Nystr\u00f6mformer", "QDQBert", "RemBERT", "RoBERTa", "RoBERTa-PreLayerNorm", "RoCBert", "RoFormer", "SqueezeBERT", "XLM", "XLM-RoBERTa", "XLM-RoBERTa-XL", "XLNet", "X-MOD", "YOSO"], "AutoModelClass": "AutoModelForMultipleChoice", "dataset": "swag", "model_used": "bert-base-uncased"}}