{"task":"Question Answering","dataset":"MultiRC","metric_names":["F1","EM"],"rows":[{"id":23267,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"PaLM 540B (finetuned) ","metrics":{"EM":"69.2","F1":"90.1"},"paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_date":"2022-04-05","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23268,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"ST-MoE-32B 269B (fine-tuned)","metrics":{"F1":"89.6"},"paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","paper_date":"2022-02-17","code_links":[{"title":"tensorflow/mesh","url":"https://github.com/tensorflow/mesh"},{"title":"xuefuzhao/openmoe","url":"https://github.com/xuefuzhao/openmoe"},{"title":"yikangshen/megablocks","url":"https://github.com/yikangshen/megablocks"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23269,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Turing NLR v5 XXL 5.4B (fine-tuned)","metrics":{"EM":"63","F1":"88.4"},"paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","paper_date":"2022-12-04","code_links":[],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23270,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"DeBERTa-1.5B","metrics":{"EM":"63.7","F1":"88.2"},"paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","paper_date":"2020-06-05","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"microsoft/DeBERTa","url":"https://github.com/microsoft/DeBERTa"},{"title":"osu-nlp-group/mind2web","url":"https://github.com/osu-nlp-group/mind2web"},{"title":"neuralmind-ai/coliee","url":"https://github.com/neuralmind-ai/coliee"},{"title":"huberemanuel/DeBERTa","url":"https://github.com/huberemanuel/DeBERTa"},{"title":"Jason-J-Choi/DeBERTa_TxtClassifier","url":"https://github.com/Jason-J-Choi/DeBERTa_TxtClassifier"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/deberta"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/deberta_v2"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/deberta_v2"},{"title":"JONGWE1/Paddle-DeBERTa","url":"https://github.com/JONGWE1/Paddle-DeBERTa"},{"title":"Mind23-2/MindCode-161","url":"https://github.com/Mind23-2/MindCode-161"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/deberta"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/deberta_v2"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23271,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Vega v2 6B (fine-tuned)","metrics":{"EM":"62.4","F1":"88.2"},"paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","paper_date":"2022-12-04","code_links":[],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23272,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"PaLM 2-L (one-shot)","metrics":{"F1":"88.2"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23273,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"T5-XXL 11B (fine-tuned)","metrics":{"F1":"88.1"},"paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","paper_date":"2019-10-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23274,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"F1":"86"},"paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","paper_date":"2022-02-17","code_links":[{"title":"tensorflow/mesh","url":"https://github.com/tensorflow/mesh"},{"title":"xuefuzhao/openmoe","url":"https://github.com/xuefuzhao/openmoe"},{"title":"yikangshen/megablocks","url":"https://github.com/yikangshen/megablocks"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23275,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"PaLM 2-M (one-shot)","metrics":{"F1":"84.1"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23276,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"PaLM 2-S (one-shot)","metrics":{"F1":"84.0"},"paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","paper_date":"2023-05-17","code_links":[{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23277,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"FLAN 137B (prompt-tuned)","metrics":{"F1":"83.4"},"paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","paper_date":"2021-09-03","code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23278,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"FLAN 137B (zero-shot)","metrics":{"F1":"77.5"},"paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","paper_date":"2021-09-03","code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23279,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"GPT-3 175B (Few-Shot)","metrics":{"F1":"75.4"},"paper_url":"https://arxiv.org/abs/2005.14165v4","paper_title":"Language Models are Few-Shot Learners","paper_date":"2020-05-28","code_links":[{"title":"ggml-org/llama.cpp","url":"https://github.com/ggml-org/llama.cpp"},{"title":"ggerganov/llama.cpp","url":"https://github.com/ggerganov/llama.cpp"},{"title":"karpathy/llm.c","url":"https://github.com/karpathy/llm.c"},{"title":"openai/gpt-3","url":"https://github.com/openai/gpt-3"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt-3"},{"title":"EleutherAI/lm_evaluation_harness","url":"https://github.com/EleutherAI/lm_evaluation_harness"},{"title":"EleutherAI/lm-evaluation-harness","url":"https://github.com/EleutherAI/lm-evaluation-harness"},{"title":"EleutherAI/gpt-neo","url":"https://github.com/EleutherAI/gpt-neo"},{"title":"karpathy/build-nanogpt","url":"https://github.com/karpathy/build-nanogpt"},{"title":"ncoop57/gpt-code-clippy","url":"https://github.com/ncoop57/gpt-code-clippy"},{"title":"codedotal/gpt-code-clippy","url":"https://github.com/codedotal/gpt-code-clippy"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"bigscience-workshop/Megatron-DeepSpeed","url":"https://github.com/bigscience-workshop/Megatron-DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"},{"title":"RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox"},{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"allenai/macaw","url":"https://github.com/allenai/macaw"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"tonyzhaozh/few-shot-learning","url":"https://github.com/tonyzhaozh/few-shot-learning"},{"title":"haiyang-w/git","url":"https://github.com/haiyang-w/git"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/gpt"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"ethanjperez/true_few_shot","url":"https://github.com/ethanjperez/true_few_shot"},{"title":"ai21labs/lm-evaluation","url":"https://github.com/ai21labs/lm-evaluation"},{"title":"lambert-x/prolab","url":"https://github.com/lambert-x/prolab"},{"title":"asahi417/relbert","url":"https://github.com/asahi417/relbert"},{"title":"grantslatton/llama.cpp","url":"https://github.com/grantslatton/llama.cpp"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"turkunlp/megatron-deepspeed","url":"https://github.com/turkunlp/megatron-deepspeed"},{"title":"contextlab/abstract2paper","url":"https://github.com/contextlab/abstract2paper"},{"title":"kyegomez/GPT3","url":"https://github.com/kyegomez/GPT3"},{"title":"Samyu0304/thought-propagation","url":"https://github.com/Samyu0304/thought-propagation"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"smile-data/smile","url":"https://github.com/smile-data/smile"},{"title":"postech-ami/smile-dataset","url":"https://github.com/postech-ami/smile-dataset"},{"title":"opengptx/lm-evaluation-harness","url":"https://github.com/opengptx/lm-evaluation-harness"},{"title":"gmum/dl-mo-2021","url":"https://github.com/gmum/dl-mo-2021"},{"title":"fywalter/label-bias","url":"https://github.com/fywalter/label-bias"},{"title":"nlx-group/overlapy","url":"https://github.com/nlx-group/overlapy"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"insait-institute/lm-evaluation-harness-bg","url":"https://github.com/insait-institute/lm-evaluation-harness-bg"},{"title":"x-lance/neusym-rag","url":"https://github.com/x-lance/neusym-rag"},{"title":"crazydigger/Callibration-of-GPT","url":"https://github.com/crazydigger/Callibration-of-GPT"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"vilm-ai/viet-llm-eval","url":"https://github.com/vilm-ai/viet-llm-eval"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"neuralmagic/lm-evaluation-harness","url":"https://github.com/neuralmagic/lm-evaluation-harness"},{"title":"scrayish/ML_NLP","url":"https://github.com/scrayish/ML_NLP"},{"title":"sambanova/lm-evaluation-harness","url":"https://github.com/sambanova/lm-evaluation-harness"},{"title":"roberttwomey/machine-imagination-isea","url":"https://github.com/roberttwomey/machine-imagination-isea"},{"title":"ltruncel/Microsoft_Azure_50daysofudacity","url":"https://github.com/ltruncel/Microsoft_Azure_50daysofudacity"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"juletx/lm-evaluation-harness","url":"https://github.com/juletx/lm-evaluation-harness"},{"title":"national-center-for-ai-saudi-arabia/lm-evaluation-harness","url":"https://github.com/national-center-for-ai-saudi-arabia/lm-evaluation-harness"},{"title":"hilberthit/gpt-3","url":"https://github.com/hilberthit/gpt-3"},{"title":"longhao-chen/aicas2024","url":"https://github.com/longhao-chen/aicas2024"},{"title":"EightRice/atn_GPT-3","url":"https://github.com/EightRice/atn_GPT-3"},{"title":"Mind23-2/MindCode-138","url":"https://github.com/Mind23-2/MindCode-138"},{"title":"mbzuai-paris/lm-evaluation-harness-atlas-chat","url":"https://github.com/mbzuai-paris/lm-evaluation-harness-atlas-chat"},{"title":"Sypherd/lm-evaluation-harness","url":"https://github.com/Sypherd/lm-evaluation-harness"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"},{"title":"zphang/lm_evaluation_harness","url":"https://github.com/zphang/lm_evaluation_harness"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23280,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"FLAN 137B (1-shot)","metrics":{"F1":"72.1"},"paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","paper_date":"2021-09-03","code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23281,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"KELM (finetuning BERT-large based single model)","metrics":{"EM":"27.2","F1":"70.8"},"paper_url":"https://arxiv.org/abs/2109.04223v2","paper_title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","paper_date":"2021-09-09","code_links":[{"title":"nlp-anonymous-happy/anonymous-kg-guided-nlp","url":"https://github.com/nlp-anonymous-happy/anonymous-kg-guided-nlp"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23282,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"BERT-large(single model)","metrics":{"EM":"24.1","F1":"70.0"},"paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","paper_date":"2018-10-11","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp"},{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"google-research/bert","url":"https://github.com/google-research/bert"},{"title":"graykode/nlp-tutorial","url":"https://github.com/graykode/nlp-tutorial"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP"},{"title":"brightmart/text_classification","url":"https://github.com/brightmart/text_classification"},{"title":"PaddlePaddle/models","url":"https://github.com/PaddlePaddle/models"},{"title":"codertimo/BERT-pytorch","url":"https://github.com/codertimo/BERT-pytorch"},{"title":"bentrevett/pytorch-sentiment-analysis","url":"https://github.com/bentrevett/pytorch-sentiment-analysis"},{"title":"pytorch/text","url":"https://github.com/pytorch/text"},{"title":"shreyashankar/gpt3-sandbox","url":"https://github.com/shreyashankar/gpt3-sandbox"},{"title":"brightmart/roberta_zh","url":"https://github.com/brightmart/roberta_zh"},{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"CyberZHG/keras-bert","url":"https://github.com/CyberZHG/keras-bert"},{"title":"alibaba/EasyNLP","url":"https://github.com/alibaba/EasyNLP"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"deepset-ai/FARM","url":"https://github.com/deepset-ai/FARM"},{"title":"ProsusAI/finBERT","url":"https://github.com/ProsusAI/finBERT"},{"title":"yoshitomo-matsubara/torchdistill","url":"https://github.com/yoshitomo-matsubara/torchdistill"},{"title":"Tencent/TurboTransformers","url":"https://github.com/Tencent/TurboTransformers"},{"title":"kyzhouhzau/BERT-NER","url":"https://github.com/kyzhouhzau/BERT-NER"},{"title":"kamalkraj/BERT_NER","url":"https://github.com/kamalkraj/BERT_NER"},{"title":"lonePatient/Bert-Multi-Label-Text-Classification","url":"https://github.com/lonePatient/Bert-Multi-Label-Text-Classification"},{"title":"Y1ran/NLP-BERT--ChineseVersion","url":"https://github.com/Y1ran/NLP-BERT--ChineseVersion"},{"title":"lukemelas/PyTorch-Pretrained-ViT","url":"https://github.com/lukemelas/PyTorch-Pretrained-ViT"},{"title":"kpe/bert-for-tf2","url":"https://github.com/kpe/bert-for-tf2"},{"title":"IndicoDataSolutions/finetune","url":"https://github.com/IndicoDataSolutions/finetune"},{"title":"Unbabel/COMET","url":"https://github.com/Unbabel/COMET"},{"title":"google-research/bigbird","url":"https://github.com/google-research/bigbird"},{"title":"dhlee347/pytorchic-bert","url":"https://github.com/dhlee347/pytorchic-bert"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"re-search/DocProduct","url":"https://github.com/re-search/DocProduct"},{"title":"kpot/keras-transformer","url":"https://github.com/kpot/keras-transformer"},{"title":"imgarylai/bert-embedding","url":"https://github.com/imgarylai/bert-embedding"},{"title":"lemonhu/ner-bert-pytorch","url":"https://github.com/lemonhu/ner-bert-pytorch"},{"title":"R1j1t/contextualSpellCheck","url":"https://github.com/R1j1t/contextualSpellCheck"},{"title":"sberbank-ai/ner-bert","url":"https://github.com/sberbank-ai/ner-bert"},{"title":"kamalkraj/BERT-SQuAD","url":"https://github.com/kamalkraj/BERT-SQuAD"},{"title":"Microsoft/AzureML-BERT","url":"https://github.com/Microsoft/AzureML-BERT"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"pengming617/bert_classification","url":"https://github.com/pengming617/bert_classification"},{"title":"awslabs/mlm-scoring","url":"https://github.com/awslabs/mlm-scoring"},{"title":"piegu/language-models","url":"https://github.com/piegu/language-models"},{"title":"charles9n/bert-sklearn","url":"https://github.com/charles9n/bert-sklearn"},{"title":"kyubyong/bert_ner","url":"https://github.com/kyubyong/bert_ner"},{"title":"louis-udm/ner-bert-crf","url":"https://github.com/louis-udm/ner-bert-crf"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"AtmaHou/MetaDialog","url":"https://github.com/AtmaHou/MetaDialog"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/bert"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/official/nlp/bert_thor"},{"title":"salesforce/GeDi","url":"https://github.com/salesforce/GeDi"},{"title":"helboukkouri/character-bert","url":"https://github.com/helboukkouri/character-bert"},{"title":"meelfy/pytorch_pretrained_bert","url":"https://github.com/meelfy/pytorch_pretrained_bert"},{"title":"google-deepmind/xquad","url":"https://github.com/google-deepmind/xquad"},{"title":"deepmind/xquad","url":"https://github.com/deepmind/xquad"},{"title":"BinWang28/BERT_Sentence_Embedding","url":"https://github.com/BinWang28/BERT_Sentence_Embedding"},{"title":"BinWang28/SBERT-WK-Sentence-Embedding","url":"https://github.com/BinWang28/SBERT-WK-Sentence-Embedding"},{"title":"glassroom/heinsen_routing","url":"https://github.com/glassroom/heinsen_routing"},{"title":"chiayewken/bert-qa","url":"https://github.com/chiayewken/bert-qa"},{"title":"chambliss/Multilingual_NER","url":"https://github.com/chambliss/Multilingual_NER"},{"title":"epfml/collaborative-attention","url":"https://github.com/epfml/collaborative-attention"},{"title":"manideep2510/siamese-BERT-fake-news-detection-LIAR","url":"https://github.com/manideep2510/siamese-BERT-fake-news-detection-LIAR"},{"title":"chujiezheng/ChID-Dataset","url":"https://github.com/chujiezheng/ChID-Dataset"},{"title":"zhengcj1/ChID-Dataset","url":"https://github.com/zhengcj1/ChID-Dataset"},{"title":"lvyufeng/mindspore-nlp-tutorial","url":"https://github.com/lvyufeng/mindspore-nlp-tutorial"},{"title":"wenhuchen/HDSA-Dialog","url":"https://github.com/wenhuchen/HDSA-Dialog"},{"title":"KeithGalli/pycon2020","url":"https://github.com/KeithGalli/pycon2020"},{"title":"ymcui/LAMB_Optimizer_TF","url":"https://github.com/ymcui/LAMB_Optimizer_TF"},{"title":"Sanyuan-Chen/RecAdam","url":"https://github.com/Sanyuan-Chen/RecAdam"},{"title":"mindspore-lab/mindnlp","url":"https://github.com/mindspore-lab/mindnlp/blob/master/mindnlp/models/bert/bert.py"},{"title":"ganeshjawahar/interpret_bert","url":"https://github.com/ganeshjawahar/interpret_bert"},{"title":"joongbo/tta","url":"https://github.com/joongbo/tta"},{"title":"dreamgonfly/BERT-pytorch","url":"https://github.com/dreamgonfly/BERT-pytorch"},{"title":"yifding/hetseq","url":"https://github.com/yifding/hetseq"},{"title":"musixmatchresearch/umberto","url":"https://github.com/musixmatchresearch/umberto"},{"title":"lonePatient/BERT-chinese-text-classification-pytorch","url":"https://github.com/lonePatient/BERT-chinese-text-classification-pytorch"},{"title":"athms/learning-from-brains","url":"https://github.com/athms/learning-from-brains"},{"title":"MLH-Fellowship/Social-BERTerfly","url":"https://github.com/MLH-Fellowship/Social-BERTerfly"},{"title":"Kyubyong/bert-token-embeddings","url":"https://github.com/Kyubyong/bert-token-embeddings"},{"title":"wzzzd/LM_NER","url":"https://github.com/wzzzd/LM_NER"},{"title":"writerai/fitbert","url":"https://github.com/writerai/fitbert"},{"title":"Qordobacode/fitbert","url":"https://github.com/Qordobacode/fitbert"},{"title":"okanvk/ENELPI---Soru-Cevap-Sistemi","url":"https://github.com/okanvk/ENELPI---Soru-Cevap-Sistemi"},{"title":"okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset","url":"https://github.com/okanvk/Turkish-Reading-Comprehension-Question-Answering-Dataset"},{"title":"whqwill/seq2seq-keyphrase-bert","url":"https://github.com/whqwill/seq2seq-keyphrase-bert"},{"title":"sagorbrur/bangla-bert","url":"https://github.com/sagorbrur/bangla-bert"},{"title":"avichaychriqui/HeBERT","url":"https://github.com/avichaychriqui/HeBERT"},{"title":"deepmipt/Slavic-BERT-NER","url":"https://github.com/deepmipt/Slavic-BERT-NER"},{"title":"reppy4620/Dialog","url":"https://github.com/reppy4620/Dialog"},{"title":"airsplay/vimpac","url":"https://github.com/airsplay/vimpac"},{"title":"huanghonggit/Mask-Language-Model","url":"https://github.com/huanghonggit/Mask-Language-Model"},{"title":"maknotavailable/pytorch-pretrained-bert","url":"https://github.com/maknotavailable/pytorch-pretrained-bert"},{"title":"Skumarr53/Attention-is-All-you-Need-PyTorch","url":"https://github.com/Skumarr53/Attention-is-All-you-Need-PyTorch"},{"title":"deping-1/2019-false-news-detection-challenge","url":"https://github.com/deping-1/2019-false-news-detection-challenge"},{"title":"lvyufeng/Cybertron","url":"https://github.com/lvyufeng/Cybertron/blob/master/cybertron/models/bert.py"},{"title":"babelscape/wikineural","url":"https://github.com/babelscape/wikineural"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms"},{"title":"aws-samples/amazon-sagemaker-bert-pytorch","url":"https://github.com/aws-samples/amazon-sagemaker-bert-pytorch"},{"title":"sajjjadayobi/ParsBigBird","url":"https://github.com/sajjjadayobi/ParsBigBird"},{"title":"CVxTz/music_genre_classification","url":"https://github.com/CVxTz/music_genre_classification"},{"title":"qywu/Chinese-GPT","url":"https://github.com/qywu/Chinese-GPT"},{"title":"phohenecker/pytorch-transformer","url":"https://github.com/phohenecker/pytorch-transformer"},{"title":"lonePatient/ERNIE-text-classification-pytorch","url":"https://github.com/lonePatient/ERNIE-text-classification-pytorch"},{"title":"IBM/MAX-Text-Sentiment-Classifier","url":"https://github.com/IBM/MAX-Text-Sentiment-Classifier"},{"title":"ericperfect/Bert_Position_BiLSTM_Attention_CRF_LSTMDecoder","url":"https://github.com/ericperfect/Bert_Position_BiLSTM_Attention_CRF_LSTMDecoder"},{"title":"duyunshu/bert-sentiment-analysis","url":"https://github.com/duyunshu/bert-sentiment-analysis"},{"title":"andi611/Mockingjay-Speech-Representation","url":"https://github.com/andi611/Mockingjay-Speech-Representation"},{"title":"SatyamSoni23/Smart-Question-Answering-System-on-Document","url":"https://github.com/SatyamSoni23/Smart-Question-Answering-System-on-Document"},{"title":"IBM/MAX-Toxic-Comment-Classifier","url":"https://github.com/IBM/MAX-Toxic-Comment-Classifier"},{"title":"ShivamRajSharma/Transformer-Architectures-From-Scratch","url":"https://github.com/ShivamRajSharma/Transformer-Architectures-From-Scratch"},{"title":"bit-ml/anoshift","url":"https://github.com/bit-ml/anoshift"},{"title":"skoltech-nlp/rudetoxifier","url":"https://github.com/skoltech-nlp/rudetoxifier"},{"title":"lonePatient/bert-sentence-similarity-pytorch","url":"https://github.com/lonePatient/bert-sentence-similarity-pytorch"},{"title":"tugstugi/mongolian-bert","url":"https://github.com/tugstugi/mongolian-bert"},{"title":"TeamLab/bert-gcn-for-paper-citation","url":"https://github.com/TeamLab/bert-gcn-for-paper-citation"},{"title":"wzzzd/Pretrain_Bert_with_MaskLM","url":"https://github.com/wzzzd/Pretrain_Bert_with_MaskLM"},{"title":"anton-bushuiev/ppiformer","url":"https://github.com/anton-bushuiev/ppiformer"},{"title":"Karthik-Bhaskar/Context-Based-Question-Answering","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering"},{"title":"KomorebiLHX/Emotion-Recognition-in-Conversations","url":"https://github.com/KomorebiLHX/Emotion-Recognition-in-Conversations"},{"title":"stefan-it/europeana-bert","url":"https://github.com/stefan-it/europeana-bert"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"khalidsaifullaah/bertify","url":"https://github.com/khalidsaifullaah/bertify"},{"title":"benywon/ReCO","url":"https://github.com/benywon/ReCO"},{"title":"thunlp/ReInfoSelect","url":"https://github.com/thunlp/ReInfoSelect"},{"title":"noise-learning/selfmix","url":"https://github.com/noise-learning/selfmix"},{"title":"lyccol/CodeBERT-based-webshell-detection","url":"https://github.com/lyccol/CodeBERT-based-webshell-detection"},{"title":"sagorbrur/codeswitch","url":"https://github.com/sagorbrur/codeswitch"},{"title":"KnightZhang625/BERT_TF","url":"https://github.com/KnightZhang625/BERT_TF"},{"title":"Farahn/AES","url":"https://github.com/Farahn/AES"},{"title":"geondopark/ckd","url":"https://github.com/geondopark/ckd"},{"title":"IBM/MAX-Question-Answering","url":"https://github.com/IBM/MAX-Question-Answering"},{"title":"benywon/ChiQA","url":"https://github.com/benywon/ChiQA"},{"title":"AdamStein97/Semi-Supervised-BERT-NER","url":"https://github.com/AdamStein97/Semi-Supervised-BERT-NER"},{"title":"LorenzoAgnolucci/BERT_for_ABSA","url":"https://github.com/LorenzoAgnolucci/BERT_for_ABSA"},{"title":"devJWSong/bert-crf-entity-recognition-pytorch","url":"https://github.com/devJWSong/bert-crf-entity-recognition-pytorch"},{"title":"ypeleg/MinimalIsAllYouNeed","url":"https://github.com/ypeleg/MinimalIsAllYouNeed"},{"title":"ilhamfp/indonesian-text-classification-multilingual","url":"https://github.com/ilhamfp/indonesian-text-classification-multilingual"},{"title":"sunyilgdx/prompts4keras","url":"https://github.com/sunyilgdx/prompts4keras"},{"title":"AutomatedProgramRepair-2021/dear-auto-fix","url":"https://github.com/AutomatedProgramRepair-2021/dear-auto-fix"},{"title":"Impavidity/relogic","url":"https://github.com/Impavidity/relogic"},{"title":"MalteHB/-l-ctra","url":"https://github.com/MalteHB/-l-ctra"},{"title":"octanove/grammartagger","url":"https://github.com/octanove/grammartagger"},{"title":"abhilash1910/BERTSimilarity","url":"https://github.com/abhilash1910/BERTSimilarity"},{"title":"overfitter/biobert_embedding","url":"https://github.com/overfitter/biobert_embedding"},{"title":"linlei1214/SITS-BERT","url":"https://github.com/linlei1214/SITS-BERT"},{"title":"benywon/ChineseBert","url":"https://github.com/benywon/ChineseBert"},{"title":"brightmart/bert_customized","url":"https://github.com/brightmart/bert_customized"},{"title":"uva-dsa/ems-pipeline","url":"https://github.com/uva-dsa/ems-pipeline"},{"title":"ElizaLo/Question-Answering-based-on-SQuAD","url":"https://github.com/ElizaLo/Question-Answering-based-on-SQuAD"},{"title":"af-ai-center/nerblackbox","url":"https://github.com/af-ai-center/nerblackbox"},{"title":"flxst/nerblackbox","url":"https://github.com/flxst/nerblackbox"},{"title":"SkullFang/BERT_NLP_Classification","url":"https://github.com/SkullFang/BERT_NLP_Classification"},{"title":"GauthierDmn/question_answering","url":"https://github.com/GauthierDmn/question_answering"},{"title":"ABaldrati/MT-BERT","url":"https://github.com/ABaldrati/MT-BERT"},{"title":"Colanim/BERT_STS-B","url":"https://github.com/Colanim/BERT_STS-B"},{"title":"guoyaohua/BERT-Chinese-Annotation","url":"https://github.com/guoyaohua/BERT-Chinese-Annotation"},{"title":"Kanishkparganiha/Named-Entity-Recognition-using-BERT-with-PyTorch","url":"https://github.com/Kanishkparganiha/Named-Entity-Recognition-using-BERT-with-PyTorch"},{"title":"mkavim/finetune_bert","url":"https://github.com/mkavim/finetune_bert"},{"title":"guoyaohua/BERT-Classifier","url":"https://github.com/guoyaohua/BERT-Classifier"},{"title":"HuihuiChyan/BJTUNLP_Practice2020","url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2020"},{"title":"stefan-it/historic-ner","url":"https://github.com/stefan-it/historic-ner"},{"title":"baotramduong/Sentiment-Analysis-with-Deep-Learning-using-BERT","url":"https://github.com/baotramduong/Sentiment-Analysis-with-Deep-Learning-using-BERT"},{"title":"dbmdz/historic-ner","url":"https://github.com/dbmdz/historic-ner"},{"title":"baotramduong/Twitter-Sentiment-Analysis-with-Deep-Learning-using-BERT","url":"https://github.com/baotramduong/Twitter-Sentiment-Analysis-with-Deep-Learning-using-BERT"},{"title":"MansMeg/IntroML","url":"https://github.com/MansMeg/IntroML"},{"title":"bino282/bert4news","url":"https://github.com/bino282/bert4news"},{"title":"benywon/ComQA","url":"https://github.com/benywon/ComQA"},{"title":"madhawav/MML","url":"https://github.com/madhawav/MML"},{"title":"uygarkurt/BERT-PyTorch","url":"https://github.com/uygarkurt/BERT-PyTorch"},{"title":"xiangyue9607/CliniRC","url":"https://github.com/xiangyue9607/CliniRC"},{"title":"SindhuMadi/FakeNewsDetection","url":"https://github.com/SindhuMadi/FakeNewsDetection"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/bert"},{"title":"ambityga/memsem","url":"https://github.com/ambityga/memsem"},{"title":"debnsuma/Intro-Transformer-BERT","url":"https://github.com/debnsuma/Intro-Transformer-BERT"},{"title":"cybertronai/megatron-lm","url":"https://github.com/cybertronai/megatron-lm"},{"title":"smarton-empower/smarton-ai","url":"https://github.com/smarton-empower/smarton-ai"},{"title":"SAP-samples/acl2019-commonsense","url":"https://github.com/SAP-samples/acl2019-commonsense"},{"title":"SAP-samples/acl2019-commonsense-reasoning","url":"https://github.com/SAP-samples/acl2019-commonsense-reasoning"},{"title":"lcs2-iiitd/emotion-flip-reasoning","url":"https://github.com/lcs2-iiitd/emotion-flip-reasoning"},{"title":"han-shi/SparseBERT","url":"https://github.com/han-shi/SparseBERT"},{"title":"davidbellamy/labrador","url":"https://github.com/davidbellamy/labrador"},{"title":"heraclex12/vietpunc","url":"https://github.com/heraclex12/vietpunc"},{"title":"DimasDMM/nlp-completer","url":"https://github.com/DimasDMM/nlp-completer"},{"title":"af-ai-center/bert","url":"https://github.com/af-ai-center/bert"},{"title":"Jackma3/NER-Bert-BiLstm","url":"https://github.com/Jackma3/NER-Bert-BiLstm"},{"title":"eagle705/bert","url":"https://github.com/eagle705/bert"},{"title":"DimasDMM/transformers","url":"https://github.com/DimasDMM/transformers"},{"title":"fancyerii/bert","url":"https://github.com/fancyerii/bert"},{"title":"cedrickchee/pytorch-pretrained-BERT","url":"https://github.com/cedrickchee/pytorch-pretrained-BERT"},{"title":"Susheel-1999/Sentence_Similarity","url":"https://github.com/Susheel-1999/Sentence_Similarity"},{"title":"xiaopingzhong/bert-finetune-for-classfier","url":"https://github.com/xiaopingzhong/bert-finetune-for-classfier"},{"title":"SYangDong/bert-with-frozen-code","url":"https://github.com/SYangDong/bert-with-frozen-code"},{"title":"tree-park/bert-pretrainer","url":"https://github.com/tree-park/bert-pretrainer"},{"title":"abhilashreddys/Fake-News-Article","url":"https://github.com/abhilashreddys/Fake-News-Article"},{"title":"autobotasia/vibert","url":"https://github.com/autobotasia/vibert"},{"title":"rasta-nitzsche/Bert-For-Algerian-Dialect-DariBERTo","url":"https://github.com/rasta-nitzsche/Bert-For-Algerian-Dialect-DariBERTo"},{"title":"tobyatgithub/bert_tutorial","url":"https://github.com/tobyatgithub/bert_tutorial"},{"title":"Holldean/BERT-Pruning","url":"https://github.com/Holldean/BERT-Pruning"},{"title":"mindspore-courses/ABSA-MindSpore","url":"https://github.com/mindspore-courses/ABSA-MindSpore"},{"title":"theneuralbeing/bert-finetuning-webinar","url":"https://github.com/theneuralbeing/bert-finetuning-webinar"},{"title":"HuihuiChyan/BJTUNLP_Practice2021","url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2021"},{"title":"nerdimite/bert-finetuning-webinar","url":"https://github.com/nerdimite/bert-finetuning-webinar"},{"title":"soutsios/pos-tagger-bert-tensorflow","url":"https://github.com/soutsios/pos-tagger-bert-tensorflow"},{"title":"hate-alert/indicabusive","url":"https://github.com/hate-alert/indicabusive"},{"title":"viniciusoliveirasd/bert-applications","url":"https://github.com/viniciusoliveirasd/bert-applications"},{"title":"EssayKillerBrain/NLP-BERT-Chinese","url":"https://github.com/EssayKillerBrain/NLP-BERT-Chinese"},{"title":"lehoanganh298/BERT-Question-Answering","url":"https://github.com/lehoanganh298/BERT-Question-Answering"},{"title":"derronxu/sparsebert","url":"https://github.com/derronxu/sparsebert"},{"title":"kelly2016/multi-label-bert","url":"https://github.com/kelly2016/multi-label-bert"},{"title":"nicolashernandez/readi-lrec22","url":"https://github.com/nicolashernandez/readi-lrec22"},{"title":"circlePi/BERT_Chinese_Text_Class_By_pytorch","url":"https://github.com/circlePi/BERT_Chinese_Text_Class_By_pytorch"},{"title":"gcunhase/embracebert","url":"https://github.com/gcunhase/embracebert"},{"title":"zer0sh0t/artificial_intelligence","url":"https://github.com/zer0sh0t/artificial_intelligence/tree/master/language_models/bidirectional_encoder_representations_from_transformers"},{"title":"anupamsingh610/bert_ner_stride","url":"https://github.com/anupamsingh610/bert_ner_stride"},{"title":"itsShnik/adaptively-finetuning-transformers","url":"https://github.com/itsShnik/adaptively-finetuning-transformers"},{"title":"DylanCope/Image-Captioning-with-Bimodal-Transformers","url":"https://github.com/DylanCope/Image-Captioning-with-Bimodal-Transformers"},{"title":"sydney-machine-learning/sentimentanalysis-uselections","url":"https://github.com/sydney-machine-learning/sentimentanalysis-uselections"},{"title":"arkel23/PyTorch-Pretrained-ViT","url":"https://github.com/arkel23/PyTorch-Pretrained-ViT"},{"title":"hegebharat/sentiment-Analysis-for-German-Datasets","url":"https://github.com/hegebharat/sentiment-Analysis-for-German-Datasets"},{"title":"deepmipt/bert","url":"https://github.com/deepmipt/bert/tree/feat/multi_gpu"},{"title":"ManasRMohanty/DS5500-capstone","url":"https://github.com/ManasRMohanty/DS5500-capstone"},{"title":"Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-","url":"https://github.com/Raman-Raje/Machine-Reading-Comprehension-Neural-Question-Answer-"},{"title":"karta282950/bert-multiclass","url":"https://github.com/karta282950/bert-multiclass"},{"title":"om00839/machine-suneung","url":"https://github.com/om00839/machine-suneung"},{"title":"jungomi/swiss-language-model","url":"https://github.com/jungomi/swiss-language-model"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"asgaardlab/test-case-similarity-technique","url":"https://github.com/asgaardlab/test-case-similarity-technique"},{"title":"rajlm10/Chandler","url":"https://github.com/rajlm10/Chandler"},{"title":"harenlin/IMDB-Sentiment-Analysis-Using-BERT-Fine-Tuning","url":"https://github.com/harenlin/IMDB-Sentiment-Analysis-Using-BERT-Fine-Tuning"},{"title":"noelkelias/multitok","url":"https://github.com/noelkelias/multitok"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"arielsho/decomposition-table-reasoning","url":"https://github.com/arielsho/decomposition-table-reasoning"},{"title":"scotthlee/injury_autocoding","url":"https://github.com/scotthlee/injury_autocoding"},{"title":"broccolik/BERT-NER","url":"https://github.com/broccolik/BERT-NER"},{"title":"abhaskumarsinha/Keras-implementation-of-Transformer-Architecture","url":"https://github.com/abhaskumarsinha/Keras-implementation-of-Transformer-Architecture"},{"title":"vmware-labs/bert-pretraining","url":"https://github.com/vmware-labs/bert-pretraining"},{"title":"RonRaifer/BERT-Ghazali","url":"https://github.com/RonRaifer/BERT-Ghazali"},{"title":"kobowon/cs470_project_version2","url":"https://github.com/kobowon/cs470_project_version2"},{"title":"venkyr91193/Sentiment-Analysis-with-BERT","url":"https://github.com/venkyr91193/Sentiment-Analysis-with-BERT"},{"title":"ltgoslo/assessing_and_probing_sentiment","url":"https://github.com/ltgoslo/assessing_and_probing_sentiment"},{"title":"LeoWood/bert-horovod","url":"https://github.com/LeoWood/bert-horovod"},{"title":"mocherson/aki_bert","url":"https://github.com/mocherson/aki_bert"},{"title":"polzinben/TensorFlow_NLP","url":"https://github.com/polzinben/TensorFlow_NLP"},{"title":"siramatu/brigade-visualizer","url":"https://github.com/siramatu/brigade-visualizer"},{"title":"samirsahoo007/Audio-and-Speech-Processing","url":"https://github.com/samirsahoo007/Audio-and-Speech-Processing"},{"title":"Doffery/BERT-Sentiment-Analysis-Amazon-Review","url":"https://github.com/Doffery/BERT-Sentiment-Analysis-Amazon-Review"},{"title":"venkyr91193/Sentiment_Analysis_with_BERT","url":"https://github.com/venkyr91193/Sentiment_Analysis_with_BERT"},{"title":"why2000/DuReader-bert","url":"https://github.com/why2000/DuReader-bert"},{"title":"weidafeng/NLU2019","url":"https://github.com/weidafeng/NLU2019"},{"title":"theQuert/inlpfun","url":"https://github.com/theQuert/inlpfun"},{"title":"johnr0/TaleBrush-backend","url":"https://github.com/johnr0/TaleBrush-backend"},{"title":"Jun-Zhang-32108/Sentiment-Analysis","url":"https://github.com/Jun-Zhang-32108/Sentiment-Analysis"},{"title":"MS-Mind/MS-Code-01","url":"https://github.com/MS-Mind/MS-Code-01/tree/main/soft_masked_bert"},{"title":"gouwenrui/cpe-pro-main","url":"https://github.com/gouwenrui/cpe-pro-main"},{"title":"2024-MindSpore-1/Code3","url":"https://github.com/2024-MindSpore-1/Code3/tree/main/scBERT"},{"title":"hoangtrungchinh/Bert-SQuAD-v2","url":"https://github.com/hoangtrungchinh/Bert-SQuAD-v2"},{"title":"nageshsinghc4/deepwrap","url":"https://github.com/nageshsinghc4/deepwrap"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"eaishwa/quora-ques-pair-similarity","url":"https://github.com/eaishwa/quora-ques-pair-similarity"},{"title":"rohanshad/cmr_transformer","url":"https://github.com/rohanshad/cmr_transformer"},{"title":"MichaelZhouwang/LMlexsub","url":"https://github.com/MichaelZhouwang/LMlexsub"},{"title":"the-Quert/iNLPfun","url":"https://github.com/the-Quert/iNLPfun"},{"title":"Coda-s/BJTU_NLP_Practice","url":"https://github.com/Coda-s/BJTU_NLP_Practice"},{"title":"goldenbili/bert_lamb_pretrain","url":"https://github.com/goldenbili/bert_lamb_pretrain"},{"title":"MaZhiyuanBUAA/bert-tf1.4.0","url":"https://github.com/MaZhiyuanBUAA/bert-tf1.4.0"},{"title":"dispink/xpt","url":"https://github.com/dispink/xpt"},{"title":"mirbostani/QA-KD-AL","url":"https://github.com/mirbostani/QA-KD-AL"},{"title":"abhineet/sentence_classification_pubmed_scibert","url":"https://github.com/abhineet/sentence_classification_pubmed_scibert"},{"title":"frankcgq105/BERTCHEN","url":"https://github.com/frankcgq105/BERTCHEN"},{"title":"Kerram/Deephol-Bert-Zpp","url":"https://github.com/Kerram/Deephol-Bert-Zpp"},{"title":"cospplay/bert-master","url":"https://github.com/cospplay/bert-master"},{"title":"YuanEric88/bert-nlu","url":"https://github.com/YuanEric88/bert-nlu"},{"title":"yuelinan/c3vg","url":"https://github.com/yuelinan/c3vg"},{"title":"Domminique/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI-","url":"https://github.com/Domminique/Deploy-BERT-for-Sentiment-Analysis-with-FastAPI-"},{"title":"scut-bds/example_repo_from_scutbds","url":"https://github.com/scut-bds/example_repo_from_scutbds"},{"title":"Alihassan7726/Multi-Class-classification-using-BERT-","url":"https://github.com/Alihassan7726/Multi-Class-classification-using-BERT-"},{"title":"kriesbeck/masked-language-prediction","url":"https://github.com/kriesbeck/masked-language-prediction"},{"title":"IMPLabUniPr/UniParma-at-semeval-2021-task-5","url":"https://github.com/IMPLabUniPr/UniParma-at-semeval-2021-task-5"},{"title":"SumitM0432/Quora-Insincere-Questions-Classification","url":"https://github.com/SumitM0432/Quora-Insincere-Questions-Classification"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/bert"},{"title":"AbhishekD15/Sentiment-Analysis_BERT","url":"https://github.com/AbhishekD15/Sentiment-Analysis_BERT"},{"title":"Misoknisky/Bert-MultiGpu","url":"https://github.com/Misoknisky/Bert-MultiGpu"},{"title":"thethirdwheel/malumagraph","url":"https://github.com/thethirdwheel/malumagraph"},{"title":"cmunnis/BERT_vs_Transformer-XL","url":"https://github.com/cmunnis/BERT_vs_Transformer-XL"},{"title":"brightmart/bert_original","url":"https://github.com/brightmart/bert_original"},{"title":"JNUpython/bert","url":"https://github.com/JNUpython/bert"},{"title":"Zeeshan75/Bert_Telugu_Ner","url":"https://github.com/Zeeshan75/Bert_Telugu_Ner"},{"title":"AGiannoutsos/COVID19-document-retrieval-with-BERT","url":"https://github.com/AGiannoutsos/COVID19-document-retrieval-with-BERT"},{"title":"BirgerMoell/bertcastle","url":"https://github.com/BirgerMoell/bertcastle"},{"title":"BroCoLySTyLe/SQLovaReview","url":"https://github.com/BroCoLySTyLe/SQLovaReview"},{"title":"tornermarton/bert-keras","url":"https://github.com/tornermarton/bert-keras"},{"title":"YongWookHa/BERT-on-Pytorch-Template","url":"https://github.com/YongWookHa/BERT-on-Pytorch-Template"},{"title":"yanzhitech/bert","url":"https://github.com/yanzhitech/bert"},{"title":"common-english/bert-all","url":"https://github.com/common-english/bert-all"},{"title":"JMSaindon/NlpSquad","url":"https://github.com/JMSaindon/NlpSquad"},{"title":"amauriciorr/AubreyBot","url":"https://github.com/amauriciorr/AubreyBot"},{"title":"Nilanshrajput/Intent_classification","url":"https://github.com/Nilanshrajput/Intent_classification"},{"title":"wyf-python/Bert-Pytorch-TextClassification","url":"https://github.com/wyf-python/Bert-Pytorch-TextClassification"},{"title":"teghub/TurkishNER-BERT","url":"https://github.com/teghub/TurkishNER-BERT"},{"title":"SpikeKing/My-Bert","url":"https://github.com/SpikeKing/My-Bert"},{"title":"sonalisrijan/Deep-Learning-based-Defect-Prediction-Model-for-Source-Code","url":"https://github.com/sonalisrijan/Deep-Learning-based-Defect-Prediction-Model-for-Source-Code"},{"title":"avishek-018/single_notebook_projects","url":"https://github.com/avishek-018/single_notebook_projects"},{"title":"gbcolborne/lang_id","url":"https://github.com/gbcolborne/lang_id"},{"title":"krantirk/BERT-Pretrained-model","url":"https://github.com/krantirk/BERT-Pretrained-model"},{"title":"saravanakumarjsk/BERT-collection","url":"https://github.com/saravanakumarjsk/BERT-collection"},{"title":"Katsumata420/bert_mlm","url":"https://github.com/Katsumata420/bert_mlm"},{"title":"socc-io/piqaboo","url":"https://github.com/socc-io/piqaboo"},{"title":"a414351664/Bert_MRC","url":"https://github.com/a414351664/Bert_MRC"},{"title":"zaaztt/bert_chinese_example","url":"https://github.com/zaaztt/bert_chinese_example"},{"title":"mayurnewase/Quora-Bert","url":"https://github.com/mayurnewase/Quora-Bert"},{"title":"Eeun-ju/NLP-study","url":"https://github.com/Eeun-ju/NLP-study"},{"title":"ricardordb/bert","url":"https://github.com/ricardordb/bert"},{"title":"luckynozomi/PPI_Bert","url":"https://github.com/luckynozomi/PPI_Bert"},{"title":"surancy/nlp-classification-with-BERT","url":"https://github.com/surancy/nlp-classification-with-BERT"},{"title":"hoichunlaw/COVID-BERT","url":"https://github.com/hoichunlaw/COVID-BERT"},{"title":"evtaktasheva/dependency_extraction","url":"https://github.com/evtaktasheva/dependency_extraction"},{"title":"flyliu2017/bert","url":"https://github.com/flyliu2017/bert"},{"title":"Guowei-Yan/Data","url":"https://github.com/Guowei-Yan/Data"},{"title":"h4ste/oscar","url":"https://github.com/h4ste/oscar"},{"title":"lkfo415579/MT-Readling-List","url":"https://github.com/lkfo415579/MT-Readling-List"},{"title":"vanslerry/long_text","url":"https://github.com/vanslerry/long_text"},{"title":"debnsuma/AmazonSageMaker101","url":"https://github.com/debnsuma/AmazonSageMaker101"},{"title":"jsantoso2/yelp-clone-ml-project","url":"https://github.com/jsantoso2/yelp-clone-ml-project"},{"title":"goldenbili/Bert_Test3","url":"https://github.com/goldenbili/Bert_Test3"},{"title":"coco60/bert-test","url":"https://github.com/coco60/bert-test"},{"title":"vanpersie32/Multigpu-Bert","url":"https://github.com/vanpersie32/Multigpu-Bert"},{"title":"danlim-wz/analysis_of_social_media_data_about_singapore","url":"https://github.com/danlim-wz/analysis_of_social_media_data_about_singapore"},{"title":"nicholasbao/nlp_job","url":"https://github.com/nicholasbao/nlp_job"},{"title":"shaikhzhas/bert","url":"https://github.com/shaikhzhas/bert"},{"title":"somiltg/xquad","url":"https://github.com/somiltg/xquad"},{"title":"xbtlin/All-about-Machine-Learning","url":"https://github.com/xbtlin/All-about-Machine-Learning"},{"title":"meizi1114/bert","url":"https://github.com/meizi1114/bert"},{"title":"ufal/wembedding_service","url":"https://github.com/ufal/wembedding_service"},{"title":"nmfisher/bert-modified","url":"https://github.com/nmfisher/bert-modified"},{"title":"JA-Bar/nlp-depression","url":"https://github.com/JA-Bar/nlp-depression"},{"title":"OweysMomenzada/Evergreen-Content-Classifier-for-german-Text","url":"https://github.com/OweysMomenzada/Evergreen-Content-Classifier-for-german-Text"},{"title":"wchh127/yykf","url":"https://github.com/wchh127/yykf"},{"title":"nalbarr/coursera-ai4med-course3","url":"https://github.com/nalbarr/coursera-ai4med-course3"},{"title":"appcoreopc/berty","url":"https://github.com/appcoreopc/berty"},{"title":"fabiocorreacordeiro/Elsevier_abstracts-Classification","url":"https://github.com/fabiocorreacordeiro/Elsevier_abstracts-Classification"},{"title":"Nstats/my_bert","url":"https://github.com/Nstats/my_bert"},{"title":"LoveYang/bert_test","url":"https://github.com/LoveYang/bert_test"},{"title":"mohamedateya/bert-fine-tuning-sentence-classification-for-cola","url":"https://github.com/mohamedateya/bert-fine-tuning-sentence-classification-for-cola"},{"title":"qbxlvnf11/pretrained-language-model-BERT","url":"https://github.com/qbxlvnf11/pretrained-language-model-BERT"},{"title":"davidsvaughn/dts-tf","url":"https://github.com/davidsvaughn/dts-tf"},{"title":"Alihassan7726/Fine-tuning-BERT-for-semantic-sentence-pairs-classification","url":"https://github.com/Alihassan7726/Fine-tuning-BERT-for-semantic-sentence-pairs-classification"},{"title":"xiuyu0000/tutorials","url":"https://github.com/xiuyu0000/tutorials/tree/main/bert"},{"title":"habibullah-araphat/BERT-NER-TPU","url":"https://github.com/habibullah-araphat/BERT-NER-TPU"},{"title":"RxstydnR/Stock_BERT","url":"https://github.com/RxstydnR/Stock_BERT"},{"title":"Vladimetr/ASR-Knowledge-Transferring","url":"https://github.com/Vladimetr/ASR-Knowledge-Transferring"},{"title":"AhmedYounes94/Semi-supervised-BERT-NER","url":"https://github.com/AhmedYounes94/Semi-supervised-BERT-NER"},{"title":"mtzcorporations/nlp_teamjodka","url":"https://github.com/mtzcorporations/nlp_teamjodka"},{"title":"darr/nerbert","url":"https://github.com/darr/nerbert"},{"title":"EuphoriaYan/bert_component","url":"https://github.com/EuphoriaYan/bert_component"},{"title":"Hibb-bb/ALLM","url":"https://github.com/Hibb-bb/ALLM"},{"title":"bcaitech1/p2-klue-Heeseok-Jeong","url":"https://github.com/bcaitech1/p2-klue-Heeseok-Jeong"},{"title":"binhetech/bert-application","url":"https://github.com/binhetech/bert-application"},{"title":"hegebharat/SelfDiscovery","url":"https://github.com/hegebharat/SelfDiscovery"},{"title":"Chonwai/Learning_BERT","url":"https://github.com/Chonwai/Learning_BERT"},{"title":"tdd-ai/data-collection","url":"https://github.com/tdd-ai/data-collection"},{"title":"MINGG2333/bert_ms","url":"https://github.com/MINGG2333/bert_ms"},{"title":"junhahyung/bert_finetune","url":"https://github.com/junhahyung/bert_finetune"},{"title":"Kosuke-Szk/BERT-NER-ja","url":"https://github.com/Kosuke-Szk/BERT-NER-ja"},{"title":"jageshmaharjan/BERT_Service","url":"https://github.com/jageshmaharjan/BERT_Service"},{"title":"MarcosGrzeca/drunktweets","url":"https://github.com/MarcosGrzeca/drunktweets"},{"title":"jiyuan/ainote","url":"https://github.com/jiyuan/ainote"},{"title":"qbxlvnf11/contextualized-embedding-BERT","url":"https://github.com/qbxlvnf11/contextualized-embedding-BERT"},{"title":"TOSHISTATS/Classification-of-Japanese-news-with-BERT","url":"https://github.com/TOSHISTATS/Classification-of-Japanese-news-with-BERT"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"lennonzurich/lalala","url":"https://github.com/lennonzurich/lalala"},{"title":"qbxlvnf11/BERT","url":"https://github.com/qbxlvnf11/BERT"},{"title":"Nstats/bert_senti_analysis_ch","url":"https://github.com/Nstats/bert_senti_analysis_ch"},{"title":"flyliu2017/bert_modularized","url":"https://github.com/flyliu2017/bert_modularized"},{"title":"xuzhezhaozhao/bert_reading","url":"https://github.com/xuzhezhaozhao/bert_reading"},{"title":"kiko441500/google_bert","url":"https://github.com/kiko441500/google_bert"},{"title":"abhiagg92/bert_sentiment","url":"https://github.com/abhiagg92/bert_sentiment"},{"title":"Zehui127/SQUAD_BERT","url":"https://github.com/Zehui127/SQUAD_BERT"},{"title":"UnknownGenie/altered-BERT-KPE","url":"https://github.com/UnknownGenie/altered-BERT-KPE"},{"title":"guzhang480/Google_BERT","url":"https://github.com/guzhang480/Google_BERT"},{"title":"RenXiangyuan/tf_bert","url":"https://github.com/RenXiangyuan/tf_bert"},{"title":"crx934080895/Bert-CRF_New2","url":"https://github.com/crx934080895/Bert-CRF_New2"},{"title":"diabhaque/Sixth-Sense","url":"https://github.com/diabhaque/Sixth-Sense"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"itspreeti25/Q-A-implementation-using-BERT-finetuned-on-multiple-datasets","url":"https://github.com/itspreeti25/Q-A-implementation-using-BERT-finetuned-on-multiple-datasets"},{"title":"gggggeun/DeepLearning_Architecture","url":"https://github.com/gggggeun/DeepLearning_Architecture"},{"title":"aaronHuang0121/AI-CUP-2020","url":"https://github.com/aaronHuang0121/AI-CUP-2020"},{"title":"pisalore/roberta_results","url":"https://github.com/pisalore/roberta_results"},{"title":"rohan400/PepperQA","url":"https://github.com/rohan400/PepperQA"},{"title":"StoneGH/bert","url":"https://github.com/StoneGH/bert"},{"title":"xiaopp123/bert_explain","url":"https://github.com/xiaopp123/bert_explain"},{"title":"JeheonPark596/sentimentsurvival","url":"https://github.com/JeheonPark596/sentimentsurvival"},{"title":"Xinsen-Zhang/transformer","url":"https://github.com/Xinsen-Zhang/transformer"},{"title":"MOHAMEDELDAKDOUKY/bert_adjusted","url":"https://github.com/MOHAMEDELDAKDOUKY/bert_adjusted"},{"title":"StuartCHAN/KARL","url":"https://github.com/StuartCHAN/KARL"},{"title":"goodluck4s/bert-","url":"https://github.com/goodluck4s/bert-"},{"title":"thecodemasterk/BERT","url":"https://github.com/thecodemasterk/BERT"},{"title":"dzqjorking/transpose","url":"https://github.com/dzqjorking/transpose"},{"title":"pingheng001/Cnn-Bert","url":"https://github.com/pingheng001/Cnn-Bert"},{"title":"TheNeuromancer/SentEmb","url":"https://github.com/TheNeuromancer/SentEmb"},{"title":"Arthurizijar/Bert_Airport","url":"https://github.com/Arthurizijar/Bert_Airport"},{"title":"MatthewSwahn/news-headlines-sarcasm-detector","url":"https://github.com/MatthewSwahn/news-headlines-sarcasm-detector"},{"title":"epcpu/deep-nlp-links","url":"https://github.com/epcpu/deep-nlp-links"},{"title":"chunghyunhee/twitter_disaster_NLP","url":"https://github.com/chunghyunhee/twitter_disaster_NLP"},{"title":"XINZXZHANG/Bert_repo","url":"https://github.com/XINZXZHANG/Bert_repo"},{"title":"yuhangT/tf_bert","url":"https://github.com/yuhangT/tf_bert"},{"title":"mithunpaul08/bert_tensorflow","url":"https://github.com/mithunpaul08/bert_tensorflow"},{"title":"DeligientSloth/bert-tensorflow","url":"https://github.com/DeligientSloth/bert-tensorflow"},{"title":"chandu7077/mybert","url":"https://github.com/chandu7077/mybert"},{"title":"darr/nlp_work","url":"https://github.com/darr/nlp_work"},{"title":"halo090770/bert","url":"https://github.com/halo090770/bert"},{"title":"llx666/git_demo","url":"https://github.com/llx666/git_demo"},{"title":"chalothon/BERT_Practice","url":"https://github.com/chalothon/BERT_Practice"},{"title":"ps2811/Bert-Multi-Label-Text-Classification-GitVersion","url":"https://github.com/ps2811/Bert-Multi-Label-Text-Classification-GitVersion"},{"title":"SCismycat/bert_code_view","url":"https://github.com/SCismycat/bert_code_view"},{"title":"karenacorn99/explore-bert","url":"https://github.com/karenacorn99/explore-bert"},{"title":"uabinf/nlp-fall-2019-project-shuhui_shuqu","url":"https://github.com/uabinf/nlp-fall-2019-project-shuhui_shuqu"},{"title":"knuddy/op_text","url":"https://github.com/knuddy/op_text"},{"title":"jinzhenfan/BERT","url":"https://github.com/jinzhenfan/BERT"},{"title":"Nimesh-Patel/BERT","url":"https://github.com/Nimesh-Patel/BERT"},{"title":"knuddj1/op_text","url":"https://github.com/knuddj1/op_text"},{"title":"FaskyCC/TextClassification","url":"https://github.com/FaskyCC/TextClassification"},{"title":"tvinith/bert","url":"https://github.com/tvinith/bert"},{"title":"nachiketaa/bert","url":"https://github.com/nachiketaa/bert"},{"title":"nachiketaa/BERT-pytorch","url":"https://github.com/nachiketaa/BERT-pytorch"},{"title":"Dongcf/Pytorch_Bert_Text_Classification","url":"https://github.com/Dongcf/Pytorch_Bert_Text_Classification"},{"title":"rickyHong/Google-BERT-repl","url":"https://github.com/rickyHong/Google-BERT-repl"},{"title":"EthanWYB/bert-classification","url":"https://github.com/EthanWYB/bert-classification"},{"title":"DataScienceNigeria/Supervised-NLP-from-Facebook-AI-Team","url":"https://github.com/DataScienceNigeria/Supervised-NLP-from-Facebook-AI-Team"},{"title":"maxudong1993/mybert","url":"https://github.com/maxudong1993/mybert"},{"title":"liuqiangict/lamb_optimizer","url":"https://github.com/liuqiangict/lamb_optimizer"},{"title":"YuehChuan/bert-Agus","url":"https://github.com/YuehChuan/bert-Agus"},{"title":"idiotprofessorchen/bert.github.io","url":"https://github.com/idiotprofessorchen/bert.github.io"},{"title":"TonyX19/bert_hyperpartisan","url":"https://github.com/TonyX19/bert_hyperpartisan"},{"title":"Walter-B/bert-20-classes","url":"https://github.com/Walter-B/bert-20-classes"},{"title":"yangyucheng000/bert_GPU","url":"https://github.com/yangyucheng000/bert_GPU"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/bert"},{"title":"yangyucheng000/bert_Ascend","url":"https://github.com/yangyucheng000/bert_Ascend"},{"title":"kingcong/gpu_albert","url":"https://github.com/kingcong/gpu_albert"},{"title":"MindSpore-paper-code-3/code9","url":"https://github.com/MindSpore-paper-code-3/code9/tree/main/soft_masked_bert"},{"title":"yangyucheng000/ascend_albert","url":"https://github.com/yangyucheng000/ascend_albert"},{"title":"Osobarako/alduswarrensewell","url":"https://github.com/Osobarako/alduswarrensewell"},{"title":"Gaozhen0816/BERT_QA_for_Chinese","url":"https://github.com/Gaozhen0816/BERT_QA_for_Chinese"},{"title":"zhang-huihui/git-repository","url":"https://github.com/zhang-huihui/git-repository"},{"title":"Soren-Kierkegaard/BERT-for-tweet-Classifcation","url":"https://github.com/Soren-Kierkegaard/BERT-for-tweet-Classifcation"},{"title":"eunseo1092/Graduation_project","url":"https://github.com/eunseo1092/Graduation_project"},{"title":"aleksac99/SQuAD-SR","url":"https://github.com/aleksac99/SQuAD-SR"},{"title":"luozhilin99/bert","url":"https://github.com/luozhilin99/bert"},{"title":"2023-MindSpore-1/ms-code-12","url":"https://github.com/2023-MindSpore-1/ms-code-12"},{"title":"2023-MindSpore-1/ms-code-11","url":"https://github.com/2023-MindSpore-1/ms-code-11"},{"title":"2023-MindSpore-1/ms-code-56","url":"https://github.com/2023-MindSpore-1/ms-code-56"},{"title":"TannerFry/CS522-Final-Project","url":"https://github.com/TannerFry/CS522-Final-Project"},{"title":"MindSpore-scientific/code-7","url":"https://github.com/MindSpore-scientific/code-7/tree/main/bert"},{"title":"svakulenk0/response_eval","url":"https://github.com/svakulenk0/response_eval"},{"title":"zsweet/BERT_zsw","url":"https://github.com/zsweet/BERT_zsw"},{"title":"lovedavidsilva/bert_old_version","url":"https://github.com/lovedavidsilva/bert_old_version"},{"title":"myamamoto555/tf-bert","url":"https://github.com/myamamoto555/tf-bert"},{"title":"longbowking/bert","url":"https://github.com/longbowking/bert"},{"title":"semal/bert","url":"https://github.com/semal/bert"},{"title":"Gaozhen0816/BERT_QA_For_AILaw","url":"https://github.com/Gaozhen0816/BERT_QA_For_AILaw"},{"title":"icewing1996/bert_dep","url":"https://github.com/icewing1996/bert_dep"},{"title":"NehaTamore/TextSimilarity","url":"https://github.com/NehaTamore/TextSimilarity"},{"title":"saurabhnlp/bert","url":"https://github.com/saurabhnlp/bert"},{"title":"kinimod23/NMT_Project","url":"https://github.com/kinimod23/NMT_Project"},{"title":"fciannel/bert_fciannel","url":"https://github.com/fciannel/bert_fciannel"},{"title":"TSLNIHAOGIT/bert_run","url":"https://github.com/TSLNIHAOGIT/bert_run"},{"title":"goldenbili/Bert_Test2","url":"https://github.com/goldenbili/Bert_Test2"},{"title":"jangjoongkeon/JK","url":"https://github.com/jangjoongkeon/JK"},{"title":"JohannLee1996/bert","url":"https://github.com/JohannLee1996/bert"},{"title":"kingcheng2000/bert","url":"https://github.com/kingcheng2000/bert"},{"title":"zapplea/bert","url":"https://github.com/zapplea/bert"},{"title":"roshaan7zafar/-MAX-Text-Sentiment-Classifier","url":"https://github.com/roshaan7zafar/-MAX-Text-Sentiment-Classifier"},{"title":"2023-MindSpore-1/ms-code-150","url":"https://github.com/2023-MindSpore-1/ms-code-150"},{"title":"bhavitvyamalik/bert","url":"https://github.com/bhavitvyamalik/bert"},{"title":"g-eklund/bert_tutorial","url":"https://github.com/g-eklund/bert_tutorial"},{"title":"habibullah-araphat/BERT-GPU","url":"https://github.com/habibullah-araphat/BERT-GPU"},{"title":"thanhlong1997/bert_quora","url":"https://github.com/thanhlong1997/bert_quora"},{"title":"TSLNIHAOGIT/bert","url":"https://github.com/TSLNIHAOGIT/bert"},{"title":"YYGXjpg/BERT_WL","url":"https://github.com/YYGXjpg/BERT_WL"},{"title":"haydlite/sparse-bert-ner","url":"https://github.com/haydlite/sparse-bert-ner"},{"title":"faizansuhail89/bert","url":"https://github.com/faizansuhail89/bert"},{"title":"Sikun/dlam_project","url":"https://github.com/Sikun/dlam_project"},{"title":"DeokO/bert-excercise-ongoing","url":"https://github.com/DeokO/bert-excercise-ongoing"},{"title":"yydai/bert_test","url":"https://github.com/yydai/bert_test"},{"title":"enod/arxiv-nlp-notes","url":"https://github.com/enod/arxiv-nlp-notes"},{"title":"tyxr/bert","url":"https://github.com/tyxr/bert"},{"title":"pengshuyuan/Bert","url":"https://github.com/pengshuyuan/Bert"},{"title":"TYTYTYTYTYTYTYTYTY/558-project","url":"https://github.com/TYTYTYTYTYTYTYTYTY/558-project"},{"title":"vijay120/bert","url":"https://github.com/vijay120/bert"},{"title":"Kevin-Vora/bert-embedding-gluonnlp-edit-","url":"https://github.com/Kevin-Vora/bert-embedding-gluonnlp-edit-"},{"title":"xesdiny/test-bert-master","url":"https://github.com/xesdiny/test-bert-master"},{"title":"tcnguyen/bert","url":"https://github.com/tcnguyen/bert"},{"title":"rpuiggari/bert2","url":"https://github.com/rpuiggari/bert2"},{"title":"bluejurand/Kaggle_QA_Google_Labeling","url":"https://github.com/bluejurand/Kaggle_QA_Google_Labeling"},{"title":"Mind23-2/MindCode-133","url":"https://github.com/Mind23-2/MindCode-133"},{"title":"yiyc-kor/bert-study","url":"https://github.com/yiyc-kor/bert-study"},{"title":"coronazap/bert_client","url":"https://github.com/coronazap/bert_client"},{"title":"Mind23-2/MindCode-144","url":"https://github.com/Mind23-2/MindCode-144"},{"title":"saurabhkulkarni77/BERT_multilabel","url":"https://github.com/saurabhkulkarni77/BERT_multilabel"},{"title":"junhahyung/bert_transfer","url":"https://github.com/junhahyung/bert_transfer"},{"title":"Maz101/pretrainingdataset","url":"https://github.com/Maz101/pretrainingdataset"},{"title":"Shinya-Kouda/kgc","url":"https://github.com/Shinya-Kouda/kgc"},{"title":"algharak/BERTenhance","url":"https://github.com/algharak/BERTenhance"},{"title":"FengJiaChunFromSYSU/Bert","url":"https://github.com/FengJiaChunFromSYSU/Bert"},{"title":"Priyanshiguptaaa/CoLA_Sentence_Classification_BERT","url":"https://github.com/Priyanshiguptaaa/CoLA_Sentence_Classification_BERT"},{"title":"owainwest/uniprot_bert","url":"https://github.com/owainwest/uniprot_bert"},{"title":"Linar23/Research_work","url":"https://github.com/Linar23/Research_work"},{"title":"Maz101/Bert","url":"https://github.com/Maz101/Bert"},{"title":"abmitra84/Language_Modeling","url":"https://github.com/abmitra84/Language_Modeling"},{"title":"xitianxiaofeixue/BERT","url":"https://github.com/xitianxiaofeixue/BERT"},{"title":"paolanu/BERT_epitope","url":"https://github.com/paolanu/BERT_epitope"},{"title":"cuber2460/bert","url":"https://github.com/cuber2460/bert"},{"title":"Nstats/bert_MRC","url":"https://github.com/Nstats/bert_MRC"},{"title":"DeligientSloth/QQsim","url":"https://github.com/DeligientSloth/QQsim"},{"title":"Caesarzhang/bert-zh","url":"https://github.com/Caesarzhang/bert-zh"},{"title":"joytianya/google_bert","url":"https://github.com/joytianya/google_bert"},{"title":"Yipeng91/text_classifier_pub","url":"https://github.com/Yipeng91/text_classifier_pub"},{"title":"elenalenaelena/machine-learning-viz","url":"https://github.com/elenalenaelena/machine-learning-viz"},{"title":"Charliesgithub20221030/BERT","url":"https://github.com/Charliesgithub20221030/BERT"},{"title":"mhaseeb123/DeepMSim","url":"https://github.com/mhaseeb123/DeepMSim"},{"title":"1wy/bert","url":"https://github.com/1wy/bert"},{"title":"wayalhruhi/gogle_bert","url":"https://github.com/wayalhruhi/gogle_bert"},{"title":"chen-xiong-yi/OwnBERT","url":"https://github.com/chen-xiong-yi/OwnBERT"},{"title":"sherinaseri/bert","url":"https://github.com/sherinaseri/bert"},{"title":"keiyamashita111/aaproject","url":"https://github.com/keiyamashita111/aaproject"},{"title":"TidalPaladin/neural-summarizer","url":"https://github.com/TidalPaladin/neural-summarizer"},{"title":"Satan012/BERT","url":"https://github.com/Satan012/BERT"},{"title":"pfecht/bert-exploration","url":"https://github.com/pfecht/bert-exploration"},{"title":"chrisleunglokhin/Capstone-BERT","url":"https://github.com/chrisleunglokhin/Capstone-BERT"},{"title":"haidershaour/bert","url":"https://github.com/haidershaour/bert"},{"title":"somiltg/bert","url":"https://github.com/somiltg/bert"},{"title":"tmalbonph/tcbert","url":"https://github.com/tmalbonph/tcbert"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23283,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Neo-6B (QA + WS)","metrics":{"F1":" 63.8"},"paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","paper_date":"2022-10-05","code_links":[{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"simran-arora/privacy_fm","url":"https://github.com/simran-arora/privacy_fm"},{"title":"simran-arora/focus","url":"https://github.com/simran-arora/focus"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23284,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Bloomberg GPT 50B (1-shot)","metrics":{"F1":"62.3"},"paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","paper_date":"2023-03-30","code_links":[{"title":"yangletliu/finlora","url":"https://github.com/yangletliu/finlora"},{"title":"open-finance-lab/finlora","url":"https://github.com/open-finance-lab/finlora"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23285,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"N-Grammer 343M","metrics":{"EM":"11.3","F1":"62"},"paper_url":"https://arxiv.org/abs/2207.06366v1","paper_title":"N-Grammer: Augmenting Transformers with latent n-grams","paper_date":"2022-07-13","code_links":[{"title":"tensorflow/lingvo","url":"https://github.com/tensorflow/lingvo"},{"title":"yiyixuxu/n-grammer-flax","url":"https://github.com/yiyixuxu/n-grammer-flax"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23286,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Neo-6B (few-shot)","metrics":{"F1":"60.8"},"paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","paper_date":"2022-10-05","code_links":[{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"simran-arora/privacy_fm","url":"https://github.com/simran-arora/privacy_fm"},{"title":"simran-arora/focus","url":"https://github.com/simran-arora/focus"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23287,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"AlexaTM 20B","metrics":{"F1":"59.6"},"paper_url":"https://arxiv.org/abs/2208.01448v2","paper_title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","paper_date":"2022-08-02","code_links":[{"title":"amazon-science/alexa-teacher-models","url":"https://github.com/amazon-science/alexa-teacher-models"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23288,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Neo-6B (QA)","metrics":{"F1":"58.8"},"paper_url":"https://arxiv.org/abs/2210.02441v3","paper_title":"Ask Me Anything: A simple strategy for prompting language models","paper_date":"2022-10-05","code_links":[{"title":"hazyresearch/ama_prompting","url":"https://github.com/hazyresearch/ama_prompting"},{"title":"simran-arora/privacy_fm","url":"https://github.com/simran-arora/privacy_fm"},{"title":"simran-arora/focus","url":"https://github.com/simran-arora/focus"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23289,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"BLOOM 176B (1-shot)","metrics":{"F1":"26.7"},"paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","paper_date":"2023-03-30","code_links":[{"title":"yangletliu/finlora","url":"https://github.com/yangletliu/finlora"},{"title":"open-finance-lab/finlora","url":"https://github.com/open-finance-lab/finlora"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23290,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"GPT-NeoX 20B (1-shot)","metrics":{"F1":"22.9"},"paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","paper_date":"2023-03-30","code_links":[{"title":"yangletliu/finlora","url":"https://github.com/yangletliu/finlora"},{"title":"open-finance-lab/finlora","url":"https://github.com/open-finance-lab/finlora"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23291,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"OPT 66B (1-shot)","metrics":{"F1":"18.8"},"paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","paper_date":"2023-03-30","code_links":[{"title":"yangletliu/finlora","url":"https://github.com/yangletliu/finlora"},{"title":"open-finance-lab/finlora","url":"https://github.com/open-finance-lab/finlora"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23292,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"T5-11B","metrics":{"EM":"63.3"},"paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","paper_date":"2019-10-23","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/t5"},{"title":"google-research/text-to-text-transfer-transformer","url":"https://github.com/google-research/text-to-text-transfer-transformer"},{"title":"amazon-science/chronos-forecasting","url":"https://github.com/amazon-science/chronos-forecasting"},{"title":"google-research/t5x","url":"https://github.com/google-research/t5x"},{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"Ki6an/fastT5","url":"https://github.com/Ki6an/fastT5"},{"title":"google/seqio","url":"https://github.com/google/seqio"},{"title":"facebookresearch/atlas","url":"https://github.com/facebookresearch/atlas"},{"title":"conceptofmind/LaMDA-pytorch","url":"https://github.com/conceptofmind/LaMDA-pytorch"},{"title":"conceptofmind/lamda-rlhf-pytorch","url":"https://github.com/conceptofmind/lamda-rlhf-pytorch"},{"title":"thu-keg/omnievent","url":"https://github.com/thu-keg/omnievent"},{"title":"asahi417/lm-question-generation","url":"https://github.com/asahi417/lm-question-generation"},{"title":"abelriboulot/onnxt5","url":"https://github.com/abelriboulot/onnxt5"},{"title":"volcengine/vegiantmodel","url":"https://github.com/volcengine/vegiantmodel"},{"title":"airc-keti/ke-t5","url":"https://github.com/airc-keti/ke-t5"},{"title":"yizhongw/tk-instruct","url":"https://github.com/yizhongw/tk-instruct"},{"title":"asahi417/lmppl","url":"https://github.com/asahi417/lmppl"},{"title":"gulucaptain/dynamictrl","url":"https://github.com/gulucaptain/dynamictrl"},{"title":"google-research/t5x_retrieval","url":"https://github.com/google-research/t5x_retrieval"},{"title":"bigscience-workshop/architecture-objective","url":"https://github.com/bigscience-workshop/architecture-objective"},{"title":"dawn0815/UniSA","url":"https://github.com/dawn0815/UniSA"},{"title":"ibm/graph_ensemble_learning","url":"https://github.com/ibm/graph_ensemble_learning"},{"title":"wangcongcong123/ttt","url":"https://github.com/wangcongcong123/ttt"},{"title":"safakkbilici/Academic-Paper-Title-Recommendation","url":"https://github.com/safakkbilici/Academic-Paper-Title-Recommendation"},{"title":"bayer-science-for-a-better-life/data2text-bioleaflets","url":"https://github.com/bayer-science-for-a-better-life/data2text-bioleaflets"},{"title":"allenai/c4-documentation","url":"https://github.com/allenai/c4-documentation"},{"title":"um-arm-lab/efficient-eng-2-ltl","url":"https://github.com/um-arm-lab/efficient-eng-2-ltl"},{"title":"lesterpjy/numeric-t5","url":"https://github.com/lesterpjy/numeric-t5"},{"title":"zhiqic/chartreader","url":"https://github.com/zhiqic/chartreader"},{"title":"LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer","url":"https://github.com/LeoLaugier/conditional-auto-encoder-text-to-text-transfer-transformer"},{"title":"s-nlp/russe_detox_2022","url":"https://github.com/s-nlp/russe_detox_2022"},{"title":"skoltech-nlp/russe_detox_2022","url":"https://github.com/skoltech-nlp/russe_detox_2022"},{"title":"jongwooko/nash-pruning-official","url":"https://github.com/jongwooko/nash-pruning-official"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/t5"},{"title":"luomancs/retriever_reader_for_okvqa","url":"https://github.com/luomancs/retriever_reader_for_okvqa"},{"title":"qipengguo/p2_webnlg2020","url":"https://github.com/qipengguo/p2_webnlg2020"},{"title":"JunnYu/x-transformers-paddle","url":"https://github.com/JunnYu/x-transformers-paddle"},{"title":"Sharif-SLPL/t5-fa","url":"https://github.com/Sharif-SLPL/t5-fa"},{"title":"shivamraval98/multitask-t5_ae","url":"https://github.com/shivamraval98/multitask-t5_ae"},{"title":"junnyu/paddle_t5","url":"https://github.com/junnyu/paddle_t5"},{"title":"ChernovAndrey/chronos-forecasting-wasserstein","url":"https://github.com/ChernovAndrey/chronos-forecasting-wasserstein"},{"title":"cccntu/ft5-demo","url":"https://github.com/cccntu/ft5-demo"},{"title":"ArvinZhuang/BiTAG","url":"https://github.com/ArvinZhuang/BiTAG"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/t5"},{"title":"cccntu/ft5-demo-space","url":"https://github.com/cccntu/ft5-demo-space"},{"title":"xuetianci/pacit","url":"https://github.com/xuetianci/pacit"},{"title":"vgaraujov/seq2seq-spanish-plms","url":"https://github.com/vgaraujov/seq2seq-spanish-plms"},{"title":"yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text","url":"https://github.com/yli-z/ml4h_are_clinical_t5_models_better_for_clinical_text"},{"title":"thecodemasterk/Text-to-Text-transfer-transformers","url":"https://github.com/thecodemasterk/Text-to-Text-transfer-transformers"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/t5"},{"title":"KAGUYAHONGLAI/SRC","url":"https://github.com/KAGUYAHONGLAI/SRC"},{"title":"Nimesh-Patel/text-to-text-transfer-transformer","url":"https://github.com/Nimesh-Patel/text-to-text-transfer-transformer"},{"title":"souvikshanku/translit-former","url":"https://github.com/souvikshanku/translit-former"},{"title":"itzprashu1/prashant","url":"https://github.com/itzprashu1/prashant"},{"title":"2023-MindSpore-1/ms-code-164","url":"https://github.com/2023-MindSpore-1/ms-code-164"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23293,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Hybrid H3 355M (3-shot, logit scoring)","metrics":{"EM":"59.7"},"paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","paper_date":"2022-12-28","code_links":[{"title":"hazyresearch/safari","url":"https://github.com/hazyresearch/safari"},{"title":"hazyresearch/h3","url":"https://github.com/hazyresearch/h3"},{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23294,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Hybrid H3 355M (0-shot, logit scoring)","metrics":{"EM":"59.5"},"paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","paper_date":"2022-12-28","code_links":[{"title":"hazyresearch/safari","url":"https://github.com/hazyresearch/safari"},{"title":"hazyresearch/h3","url":"https://github.com/hazyresearch/h3"},{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23295,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Hybrid H3 125M (0-shot, logit scoring)","metrics":{"EM":"51.4"},"paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","paper_date":"2022-12-28","code_links":[{"title":"hazyresearch/safari","url":"https://github.com/hazyresearch/safari"},{"title":"hazyresearch/h3","url":"https://github.com/hazyresearch/h3"},{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":23296,"task":"Question Answering","parent_task":null,"dataset":"MultiRC","model_name":"Hybrid H3 125M (3-shot, logit scoring)","metrics":{"EM":"48.9"},"paper_url":"https://arxiv.org/abs/2212.14052v3","paper_title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","paper_date":"2022-12-28","code_links":[{"title":"hazyresearch/safari","url":"https://github.com/hazyresearch/safari"},{"title":"hazyresearch/h3","url":"https://github.com/hazyresearch/h3"},{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"}],"metrics_order":"[\"F1\", \"EM\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}