{"task":"Language Modelling","dataset":"LAMBADA","metric_names":["Accuracy","Perplexity"],"rows":[{"id":33527,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"PaLM-540B (Few-Shot)","metrics":{"Accuracy":"89.7"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33528,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"PaLM 2-L (one-shot)","metrics":{"Accuracy":"86.9"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33529,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GPT-3 175B (Few-Shot)","metrics":{"Accuracy":"86.4","Perplexity":"1.92"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33530,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"LLaMA-65B+CFG (Zero-Shot)","metrics":{"Accuracy":"84.0"},"paper_url":"https://arxiv.org/abs/2306.17806v1","paper_title":"Stay on topic with Classifier-Free Guidance","paper_date":"2023-06-30","code_links":[],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33531,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"LLaMA-30B+CFG (zero-shot)","metrics":{"Accuracy":"83.9"},"paper_url":"https://arxiv.org/abs/2306.17806v1","paper_title":"Stay on topic with Classifier-Free Guidance","paper_date":"2023-06-30","code_links":[],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33532,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"PaLM 2-M (one-shot)","metrics":{"Accuracy":"83.7"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33533,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Cohere  Large","metrics":{"Accuracy":"82.33"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33534,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"LLaMA-13B+CFG (zero-shot)","metrics":{"Accuracy":"82.2"},"paper_url":"https://arxiv.org/abs/2306.17806v1","paper_title":"Stay on topic with Classifier-Free Guidance","paper_date":"2023-06-30","code_links":[],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33535,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"PaLM-540B (One-Shot)","metrics":{"Accuracy":"81.8"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33536,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GLaM 62B/64E (One-Shot)","metrics":{"Accuracy":"80.9"},"paper_url":"https://arxiv.org/abs/2112.06905v2","paper_title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","paper_date":"2021-12-13","code_links":[],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33537,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"PaLM 2-S (one-shot)","metrics":{"Accuracy":"80.7"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33538,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GLM-130B (bidirectional attention)","metrics":{"Accuracy":"80.2"},"paper_url":"https://arxiv.org/abs/2210.02414v2","paper_title":"GLM-130B: An Open Bilingual Pre-trained Model","paper_date":"2022-10-05","code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33539,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"SparseGPT (175B, 2:4 Sparsity)","metrics":{"Accuracy":"79.47"},"paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","paper_date":"2023-01-02","code_links":[{"title":"nvidia/tensorrt-model-optimizer","url":"https://github.com/nvidia/tensorrt-model-optimizer"},{"title":"ist-daslab/sparsegpt","url":"https://github.com/ist-daslab/sparsegpt"},{"title":"nvlabs/maskllm","url":"https://github.com/nvlabs/maskllm"},{"title":"baithebest/adagp","url":"https://github.com/baithebest/adagp"},{"title":"baithebest/sparsellm","url":"https://github.com/baithebest/sparsellm"},{"title":"eth-easl/deltazip","url":"https://github.com/eth-easl/deltazip"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33540,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"SparseGPT (175B, 4:8 Sparsity)","metrics":{"Accuracy":"78.77"},"paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","paper_date":"2023-01-02","code_links":[{"title":"nvidia/tensorrt-model-optimizer","url":"https://github.com/nvidia/tensorrt-model-optimizer"},{"title":"ist-daslab/sparsegpt","url":"https://github.com/ist-daslab/sparsegpt"},{"title":"nvlabs/maskllm","url":"https://github.com/nvlabs/maskllm"},{"title":"baithebest/adagp","url":"https://github.com/baithebest/adagp"},{"title":"baithebest/sparsellm","url":"https://github.com/baithebest/sparsellm"},{"title":"eth-easl/deltazip","url":"https://github.com/eth-easl/deltazip"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33541,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"PaLM-540B (Zero-Shot)","metrics":{"Accuracy":"77.9"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33542,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Chinchilla (Zero-Shot)","metrics":{"Accuracy":"77.7"},"paper_url":"https://arxiv.org/abs/2203.15556v1","paper_title":"Training Compute-Optimal Large Language Models","paper_date":"2022-03-29","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33543,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"SparseGPT (175B, 50% Sparsity)","metrics":{"Accuracy":"76.51"},"paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","paper_date":"2023-01-02","code_links":[{"title":"nvidia/tensorrt-model-optimizer","url":"https://github.com/nvidia/tensorrt-model-optimizer"},{"title":"ist-daslab/sparsegpt","url":"https://github.com/ist-daslab/sparsegpt"},{"title":"nvlabs/maskllm","url":"https://github.com/nvlabs/maskllm"},{"title":"baithebest/adagp","url":"https://github.com/baithebest/adagp"},{"title":"baithebest/sparsellm","url":"https://github.com/baithebest/sparsellm"},{"title":"eth-easl/deltazip","url":"https://github.com/eth-easl/deltazip"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33544,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GPT-3 175B (Zero-Shot)","metrics":{"Accuracy":"76.2","Perplexity":"3.00"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33545,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"OPT-175B","metrics":{"Accuracy":"75.59"},"paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","paper_date":"2023-01-02","code_links":[{"title":"nvidia/tensorrt-model-optimizer","url":"https://github.com/nvidia/tensorrt-model-optimizer"},{"title":"ist-daslab/sparsegpt","url":"https://github.com/ist-daslab/sparsegpt"},{"title":"nvlabs/maskllm","url":"https://github.com/nvlabs/maskllm"},{"title":"baithebest/adagp","url":"https://github.com/baithebest/adagp"},{"title":"baithebest/sparsellm","url":"https://github.com/baithebest/sparsellm"},{"title":"eth-easl/deltazip","url":"https://github.com/eth-easl/deltazip"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33546,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GPT-3 13B (Zero-Shot)","metrics":{"Accuracy":"72.5","Perplexity":"3.56"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33547,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GLM-XXLarge (bidirectional)","metrics":{"Accuracy":"72.35"},"paper_url":"https://arxiv.org/abs/2103.10360v2","paper_title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","paper_date":"2021-03-18","code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"BBuf/GLM","url":"https://github.com/BBuf/GLM"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33548,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Pythia 12B (0-shot)","metrics":{"Accuracy":"70.46"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33549,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GPT-3 6.7B (Zero-Shot)","metrics":{"Accuracy":"70.3","Perplexity":"4.00"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33550,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GPT-J-6B","metrics":{"Accuracy":"69.7","Perplexity":"3.99"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33551,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Mamba-2.8B","metrics":{"Accuracy":"69.2","Perplexity":"4.23"},"paper_url":"https://arxiv.org/abs/2312.00752v2","paper_title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","paper_date":"2023-12-01","code_links":[{"title":"state-spaces/mamba","url":"https://github.com/state-spaces/mamba"},{"title":"hustvl/vim","url":"https://github.com/hustvl/vim"},{"title":"johnma2006/mamba-minimal","url":"https://github.com/johnma2006/mamba-minimal"},{"title":"mzeromiko/vmamba","url":"https://github.com/mzeromiko/vmamba"},{"title":"havenhq/mamba-chat","url":"https://github.com/havenhq/mamba-chat"},{"title":"haiyang-w/tokenformer","url":"https://github.com/haiyang-w/tokenformer"},{"title":"Leeroo-AI/mergoo","url":"https://github.com/Leeroo-AI/mergoo"},{"title":"lmd0311/pointmamba","url":"https://github.com/lmd0311/pointmamba"},{"title":"human9000/nd-mamba2-torch","url":"https://github.com/human9000/nd-mamba2-torch"},{"title":"KyanChen/RSMamba","url":"https://github.com/KyanChen/RSMamba"},{"title":"zyphra/blackmamba","url":"https://github.com/zyphra/blackmamba"},{"title":"tommyip/mamba2-minimal","url":"https://github.com/tommyip/mamba2-minimal"},{"title":"irmvlab/point-mamba","url":"https://github.com/irmvlab/point-mamba"},{"title":"vvvm23/mamba-jax","url":"https://github.com/vvvm23/mamba-jax"},{"title":"xi-j/mamba-asr","url":"https://github.com/xi-j/mamba-asr"},{"title":"Jiaxin-Ye/DepMamba","url":"https://github.com/Jiaxin-Ye/DepMamba"},{"title":"zhangyezhuo/mamca","url":"https://github.com/zhangyezhuo/mamca"},{"title":"aiot-mlsys-lab/famba-v","url":"https://github.com/aiot-mlsys-lab/famba-v"},{"title":"weitunglin/pixmamba","url":"https://github.com/weitunglin/pixmamba"},{"title":"shendb2022/htd-mamba","url":"https://github.com/shendb2022/htd-mamba"},{"title":"thearkaprava/ms-temba","url":"https://github.com/thearkaprava/ms-temba"},{"title":"radarFudan/mamba","url":"https://github.com/radarFudan/mamba"},{"title":"AmazingDay1/TAME","url":"https://github.com/AmazingDay1/TAME"},{"title":"lab-emi/cleanumamba","url":"https://github.com/lab-emi/cleanumamba"},{"title":"weiwang31/icemamba","url":"https://github.com/weiwang31/icemamba"},{"title":"jindongjiang/slotssms","url":"https://github.com/jindongjiang/slotssms"},{"title":"anzeyimana/deepkin","url":"https://github.com/anzeyimana/deepkin"},{"title":"nus-hpc-ai-lab/dyvm","url":"https://github.com/nus-hpc-ai-lab/dyvm"},{"title":"kaviezhang/meshmamba","url":"https://github.com/kaviezhang/meshmamba"},{"title":"catalpaaa/demansia","url":"https://github.com/catalpaaa/demansia"},{"title":"zhu-0108/mts-unmixers","url":"https://github.com/zhu-0108/mts-unmixers"},{"title":"jsie7/ssm-benchmark","url":"https://github.com/jsie7/ssm-benchmark"},{"title":"khfs/DuplexMamba","url":"https://github.com/khfs/DuplexMamba"},{"title":"zzmtsvv/mamba-interface","url":"https://github.com/zzmtsvv/mamba-interface"},{"title":"areffarhadi/mamba-asr","url":"https://github.com/areffarhadi/mamba-asr"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33552,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Pythia 6.9B (0-shot)","metrics":{"Accuracy":"67.28"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33553,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GLM-XXLarge (unidirectional)","metrics":{"Accuracy":"67.18"},"paper_url":"https://arxiv.org/abs/2103.10360v2","paper_title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","paper_date":"2021-03-18","code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"thudm/swissarmytransformer","url":"https://github.com/thudm/swissarmytransformer"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"BBuf/GLM","url":"https://github.com/BBuf/GLM"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33554,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GPT-3 2.7B (Zero-Shot)","metrics":{"Accuracy":"67.1","Perplexity":"4.60"},"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":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33555,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"GPT-2 1.5B (Zero Shot)","metrics":{"Accuracy":"63.24","Perplexity":"8.63"},"paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","paper_date":"2019-02-14","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"openai/gpt-2","url":"https://github.com/openai/gpt-2"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/gpt"},{"title":"minimaxir/gpt-2-simple","url":"https://github.com/minimaxir/gpt-2-simple"},{"title":"imcaspar/gpt2-ml","url":"https://github.com/imcaspar/gpt2-ml"},{"title":"huggingface/swift-coreml-transformers","url":"https://github.com/huggingface/swift-coreml-transformers"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/blob/master/research/nlp/gpt2"},{"title":"jankrepl/mildlyoverfitted","url":"https://github.com/jankrepl/mildlyoverfitted"},{"title":"affjljoo3581/GPT2","url":"https://github.com/affjljoo3581/GPT2"},{"title":"akanyaani/gpt-2-tensorflow2.0","url":"https://github.com/akanyaani/gpt-2-tensorflow2.0"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms"},{"title":"milmor/GPT","url":"https://github.com/milmor/GPT"},{"title":"abhaskumarsinha/MinimalGPT","url":"https://github.com/abhaskumarsinha/MinimalGPT"},{"title":"aananda-giri/gpt2-nepali","url":"https://github.com/aananda-giri/gpt2-nepali"},{"title":"akanyaani/minGPTF","url":"https://github.com/akanyaani/minGPTF"},{"title":"abhaskumarsinha/Corpus2GPT","url":"https://github.com/abhaskumarsinha/Corpus2GPT"},{"title":"VachanVY/gpt.jax","url":"https://github.com/VachanVY/gpt.jax"},{"title":"MS-P3/code5","url":"https://github.com/MS-P3/code5/tree/main/gpt2"},{"title":"ramanakshay/nanogpt","url":"https://github.com/ramanakshay/nanogpt"},{"title":"2023-MindSpore-1/ms-code-154","url":"https://github.com/2023-MindSpore-1/ms-code-154"},{"title":"varun-suresh/experiments-with-gpt2","url":"https://github.com/varun-suresh/experiments-with-gpt2"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33556,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Universal Transformer (w/ dynamic halting)","metrics":{"Accuracy":"56.25"},"paper_url":"http://arxiv.org/abs/1807.03819v3","paper_title":"Universal Transformers","paper_date":"2018-07-10","code_links":[{"title":"tensorflow/tensor2tensor","url":"https://github.com/tensorflow/tensor2tensor"},{"title":"kpot/keras-transformer","url":"https://github.com/kpot/keras-transformer"},{"title":"andreamad8/Universal-Transformer-Pytorch","url":"https://github.com/andreamad8/Universal-Transformer-Pytorch"},{"title":"MostafaDehghani/bAbI-T2T","url":"https://github.com/MostafaDehghani/bAbI-T2T"},{"title":"ypeleg/MinimalIsAllYouNeed","url":"https://github.com/ypeleg/MinimalIsAllYouNeed"},{"title":"cfiken/universal_transformer","url":"https://github.com/cfiken/universal_transformer"},{"title":"moon23k/Transformer_Archs","url":"https://github.com/moon23k/Transformer_Archs"},{"title":"sidney1505/arc_maml_transformer","url":"https://github.com/sidney1505/arc_maml_transformer"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33557,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Residual Shuffle-Exchange network","metrics":{"Accuracy":"54.34"},"paper_url":"https://arxiv.org/abs/2004.04662v4","paper_title":"Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences","paper_date":"2020-04-06","code_links":[{"title":"LUMII-Syslab/RSE","url":"https://github.com/LUMII-Syslab/RSE"},{"title":"Aroksak/RSE","url":"https://github.com/Aroksak/RSE"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33558,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Gated-Attention Reader (+ features)","metrics":{"Accuracy":"49.0"},"paper_url":"http://arxiv.org/abs/1610.08431v3","paper_title":"Broad Context Language Modeling as Reading Comprehension","paper_date":"2016-10-26","code_links":[],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33559,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"OPT-175B (50% Sparsity)","metrics":{"Accuracy":"0.02"},"paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","paper_date":"2023-01-02","code_links":[{"title":"nvidia/tensorrt-model-optimizer","url":"https://github.com/nvidia/tensorrt-model-optimizer"},{"title":"ist-daslab/sparsegpt","url":"https://github.com/ist-daslab/sparsegpt"},{"title":"nvlabs/maskllm","url":"https://github.com/nvlabs/maskllm"},{"title":"baithebest/adagp","url":"https://github.com/baithebest/adagp"},{"title":"baithebest/sparsellm","url":"https://github.com/baithebest/sparsellm"},{"title":"eth-easl/deltazip","url":"https://github.com/eth-easl/deltazip"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33560,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"test","metrics":{"Accuracy":"0.01"},"paper_url":"https://arxiv.org/abs/1909.13231v3","paper_title":"Test-Time Training with Self-Supervision for Generalization under Distribution Shifts","paper_date":"2019-09-29","code_links":[{"title":"yueatsprograms/ttt_cifar_release","url":"https://github.com/yueatsprograms/ttt_cifar_release"},{"title":"yueatsprograms/ttt_imagenet_release","url":"https://github.com/yueatsprograms/ttt_imagenet_release"},{"title":"tejas-gokhale/AGAT","url":"https://github.com/tejas-gokhale/AGAT"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33561,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Pythia 12B(Zero-Shot)","metrics":{"Perplexity":"3.92"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33562,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Pythia 6.9B(Zero-Shot)","metrics":{"Perplexity":"4.45"},"paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","paper_date":"2023-04-03","code_links":[{"title":"Lightning-AI/lit-gpt","url":"https://github.com/Lightning-AI/lit-gpt"},{"title":"jzhang38/tinyllama","url":"https://github.com/jzhang38/tinyllama"},{"title":"eleutherai/gpt-neox","url":"https://github.com/eleutherai/gpt-neox"},{"title":"eleutherai/pythia","url":"https://github.com/eleutherai/pythia"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33563,"task":"Language Modelling","parent_task":null,"dataset":"LAMBADA","model_name":"Megatron-Turing NLG 530B (Few-Shot)","metrics":{"Accuracy":"Megatron-Turing NLG 530B (Few-Shot)"},"paper_url":"https://arxiv.org/abs/2201.11990v3","paper_title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","paper_date":"2022-01-28","code_links":[{"title":"microsoft/DeepSpeed","url":"https://github.com/microsoft/DeepSpeed"},{"title":"NVIDIA/NeMo-Curator","url":"https://github.com/NVIDIA/NeMo-Curator"}],"metrics_order":"[\"Accuracy\", \"Perplexity\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]}]}