{"task":"Language Modelling","dataset":"WikiText-2","metric_names":["Test perplexity","Validation perplexity","Number of params"],"rows":[{"id":33620,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"SparseGPT (175B, 50% Sparsity)","metrics":{"Test perplexity":"8.21"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33621,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"OPT-175B","metrics":{"Test perplexity":"8.34"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33622,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"SparseGPT (175B, 4:8 Sparsity)","metrics":{"Test perplexity":"8.45"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33623,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"SparseGPT (175B, 2:4 Sparsity)","metrics":{"Test perplexity":"8.73"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33624,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"GPT-2 (fine-tuned)","metrics":{"Number of params":"1542M","Test perplexity":"15.17","Validation perplexity":"15.69"},"paper_url":"https://arxiv.org/abs/2110.08633v7","paper_title":"Hydra: A System for Large Multi-Model Deep Learning","paper_date":"2021-10-16","code_links":[{"title":"knagrecha/hydra","url":"https://github.com/knagrecha/hydra"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33625,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"GPT-2","metrics":{"Number of params":"1542M","Test perplexity":"18.34"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33626,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"GPT-2 (large)","metrics":{"Number of params":"762M","Test perplexity":"19.93"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33627,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"GPT-2 (medium)","metrics":{"Number of params":"345M","Test perplexity":"22.76"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33628,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"GPT-2 (small)","metrics":{"Number of params":"117M","Test perplexity":"29.41"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33629,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"BERT-Large-CAS","metrics":{"Number of params":"395M","Test perplexity":"34.1","Validation perplexity":"37.7"},"paper_url":"https://arxiv.org/abs/1904.09408v2","paper_title":"Language Models with Transformers","paper_date":"2019-04-20","code_links":[{"title":"cgraywang/gluon-nlp-1","url":"https://github.com/cgraywang/gluon-nlp-1"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33630,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Mogrifier LSTM + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"38.6","Validation perplexity":"40.2"},"paper_url":"https://arxiv.org/abs/1909.01792v2","paper_title":"Mogrifier LSTM","paper_date":"2019-09-04","code_links":[{"title":"deepmind/lamb","url":"https://github.com/deepmind/lamb"},{"title":"RMichaelSwan/MogrifierLSTM","url":"https://github.com/RMichaelSwan/MogrifierLSTM"},{"title":"microcoder-py/mogrifier-lstm","url":"https://github.com/microcoder-py/mogrifier-lstm"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33631,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"adversarial + AWD-LSTM-MoS + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"38.65","Validation perplexity":"40.27"},"paper_url":"https://arxiv.org/abs/1906.03805v2","paper_title":"Improving Neural Language Modeling via Adversarial Training","paper_date":"2019-06-10","code_links":[{"title":"ChengyueGongR/advsoft","url":"https://github.com/ChengyueGongR/advsoft"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33632,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"FRAGE + AWD-LSTM-MoS + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"39.14","Validation perplexity":"40.85"},"paper_url":"https://arxiv.org/abs/1809.06858v2","paper_title":"FRAGE: Frequency-Agnostic Word Representation","paper_date":"2018-09-18","code_links":[{"title":"ChengyueGongR/FrequencyAgnostic","url":"https://github.com/ChengyueGongR/FrequencyAgnostic"},{"title":"JakubStefko/w2vf","url":"https://github.com/JakubStefko/w2vf"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33633,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Past Decode Reg. + AWD-LSTM-MoS + dyn. eval.","metrics":{"Number of params":"35M","Test perplexity":"40.3","Validation perplexity":"42.0"},"paper_url":"http://arxiv.org/abs/1808.05908v4","paper_title":"Improved Language Modeling by Decoding the Past","paper_date":"2018-08-14","code_links":[],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33634,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"GL-LWGC + AWD-MoS-LSTM + dynamic eval","metrics":{"Number of params":"38M","Test perplexity":"40.46","Validation perplexity":"42.19"},"paper_url":"http://arxiv.org/abs/1708.08863v2","paper_title":"Gradual Learning of Recurrent Neural Networks","paper_date":"2017-08-29","code_links":[{"title":"zivaharoni/gradual-learning-rnn","url":"https://github.com/zivaharoni/gradual-learning-rnn"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33635,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-MoS + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"40.68","Validation perplexity":"42.41"},"paper_url":"http://arxiv.org/abs/1711.03953v4","paper_title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","paper_date":"2017-11-10","code_links":[{"title":"zihangdai/mos","url":"https://github.com/zihangdai/mos"},{"title":"cstorm125/thai2fit","url":"https://github.com/cstorm125/thai2fit"},{"title":"tdmeeste/SparseSeqModels","url":"https://github.com/tdmeeste/SparseSeqModels"},{"title":"yfreedomliTHU/mos-pytorch1.1","url":"https://github.com/yfreedomliTHU/mos-pytorch1.1"},{"title":"nkcr/overlap-ml","url":"https://github.com/nkcr/overlap-ml"},{"title":"zhangyaoyuan/GAN-Simplification","url":"https://github.com/zhangyaoyuan/GAN-Simplification"},{"title":"nunezpaul/MNIST","url":"https://github.com/nunezpaul/MNIST"},{"title":"omerlux/Recurrent_Neural_Network_-_Part_2","url":"https://github.com/omerlux/Recurrent_Neural_Network_-_Part_2"},{"title":"omerlux/NLP-PTB","url":"https://github.com/omerlux/NLP-PTB"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33636,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-DRILL + dynamic eval","metrics":{"Number of params":"34M","Test perplexity":"42.0","Validation perplexity":"43.9"},"paper_url":"https://arxiv.org/abs/1905.05513v2","paper_title":"Deep Residual Output Layers for Neural Language Generation","paper_date":"2019-05-14","code_links":[{"title":"idiap/drill","url":"https://github.com/idiap/drill"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33637,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM + dynamic eval","metrics":{"Number of params":"33M","Test perplexity":"44.3","Validation perplexity":"46.4"},"paper_url":"http://arxiv.org/abs/1709.07432v2","paper_title":"Dynamic Evaluation of Neural Sequence Models","paper_date":"2017-09-21","code_links":[{"title":"benkrause/dynamic-evaluation","url":"https://github.com/benkrause/dynamic-evaluation"},{"title":"benkrause/dynamiceval-transformer","url":"https://github.com/benkrause/dynamiceval-transformer"},{"title":"sacmehta/PRU","url":"https://github.com/sacmehta/PRU"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33638,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM + continuous cache pointer","metrics":{"Number of params":"33M","Test perplexity":"52.0","Validation perplexity":"53.8"},"paper_url":"http://arxiv.org/abs/1708.02182v1","paper_title":"Regularizing and Optimizing LSTM Language Models","paper_date":"2017-08-07","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/enas_lm"},{"title":"fastai/fastai","url":"https://github.com/fastai/fastai/blob/master/fastai/text/models/awdlstm.py"},{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"salesforce/awd-lstm-lm","url":"https://github.com/salesforce/awd-lstm-lm"},{"title":"castorini/hedwig","url":"https://github.com/castorini/hedwig"},{"title":"cstorm125/thai2fit","url":"https://github.com/cstorm125/thai2fit"},{"title":"castorini/Castor","url":"https://github.com/castorini/Castor"},{"title":"Han-JD/GRU-D","url":"https://github.com/Han-JD/GRU-D"},{"title":"iwangjian/ByteCup2018","url":"https://github.com/iwangjian/ByteCup2018"},{"title":"S-Abdelnabi/awt","url":"https://github.com/S-Abdelnabi/awt"},{"title":"Machine-Learning-Tokyo/Poetry-GAN","url":"https://github.com/Machine-Learning-Tokyo/Poetry-GAN"},{"title":"prajjwal1/language-modelling","url":"https://github.com/prajjwal1/language-modelling"},{"title":"AtheMathmo/AggMo","url":"https://github.com/AtheMathmo/AggMo"},{"title":"alexandra-chron/wassa-2018","url":"https://github.com/alexandra-chron/wassa-2018"},{"title":"alexandra-chron/ntua-slp-wassa-iest2018","url":"https://github.com/alexandra-chron/ntua-slp-wassa-iest2018"},{"title":"uclanlp/NamedEntityLanguageModel","url":"https://github.com/uclanlp/NamedEntityLanguageModel"},{"title":"mamamot/Russian-ULMFit","url":"https://github.com/mamamot/Russian-ULMFit"},{"title":"noise-field/Russian-ULMFit","url":"https://github.com/noise-field/Russian-ULMFit"},{"title":"Janus-Shiau/awd-lstm-tensorflow","url":"https://github.com/Janus-Shiau/awd-lstm-tensorflow"},{"title":"chris-tng/semi-supervised-nlp","url":"https://github.com/chris-tng/semi-supervised-nlp"},{"title":"ahmetumutdurmus/awd-lstm","url":"https://github.com/ahmetumutdurmus/awd-lstm"},{"title":"NightmareVoid/LSTM_for_EEG","url":"https://github.com/NightmareVoid/LSTM_for_EEG"},{"title":"jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"jb33k/awd-lstm-lm-ThinkNet","url":"https://github.com/jb33k/awd-lstm-lm-ThinkNet"},{"title":"rajs96/ULMFiT-Twitter-US-Airline-Sentiment","url":"https://github.com/rajs96/ULMFiT-Twitter-US-Airline-Sentiment"},{"title":"nkcr/overlap-ml","url":"https://github.com/nkcr/overlap-ml"},{"title":"jkkummerfeld/emnlp20lm","url":"https://github.com/jkkummerfeld/emnlp20lm"},{"title":"BenjiKCF/AWD-LSTM-sentiment-classifier","url":"https://github.com/BenjiKCF/AWD-LSTM-sentiment-classifier"},{"title":"mnhng/hier-char-emb","url":"https://github.com/mnhng/hier-char-emb"},{"title":"Amir-Hofo/Language_Modeling_with_LSTM_models","url":"https://github.com/Amir-Hofo/Language_Modeling_with_LSTM_models"},{"title":"SachinIchake/KALM","url":"https://github.com/SachinIchake/KALM"},{"title":"AtheMathmo/lookahead-lstm","url":"https://github.com/AtheMathmo/lookahead-lstm"},{"title":"llppff/ptb-lstmorqrnn-pytorch","url":"https://github.com/llppff/ptb-lstmorqrnn-pytorch"},{"title":"soyoung97/awd-lstm-gru","url":"https://github.com/soyoung97/awd-lstm-gru"},{"title":"Mees-Molenaar/protein_location","url":"https://github.com/Mees-Molenaar/protein_location"},{"title":"uchange/ulangel","url":"https://github.com/uchange/ulangel"},{"title":"vganesh46/awd-lstm-pytorch-implementation","url":"https://github.com/vganesh46/awd-lstm-pytorch-implementation"},{"title":"Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"arvieFrydenlund/awd-lstm-lm","url":"https://github.com/arvieFrydenlund/awd-lstm-lm"},{"title":"JessikaSmith/language_model","url":"https://github.com/JessikaSmith/language_model"},{"title":"ari-holtzman/genlm","url":"https://github.com/ari-holtzman/genlm"},{"title":"philippwirth/treelangrnn","url":"https://github.com/philippwirth/treelangrnn"},{"title":"varshinireddyt/ULMFiT","url":"https://github.com/varshinireddyt/ULMFiT"},{"title":"muellerzr/CodeFest_2019","url":"https://github.com/muellerzr/CodeFest_2019"},{"title":"philippwirth/awd-lstm-test","url":"https://github.com/philippwirth/awd-lstm-test"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33639,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-DOC x5","metrics":{"Number of params":"185M","Test perplexity":"53.09","Validation perplexity":"54.19"},"paper_url":"http://arxiv.org/abs/1808.10143v2","paper_title":"Direct Output Connection for a High-Rank Language Model","paper_date":"2018-08-30","code_links":[{"title":"nttcslab-nlp/doc_lm","url":"https://github.com/nttcslab-nlp/doc_lm"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33640,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Ensemble of All","metrics":{"Test perplexity":"53.73","Validation perplexity":"55.4"},"paper_url":"https://arxiv.org/abs/2312.03735v1","paper_title":"Advancing State of the Art in Language Modeling","paper_date":"2023-11-28","code_links":[{"title":"davidherel/sota_lm","url":"https://github.com/davidherel/sota_lm"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33641,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Mogrifier LSTM","metrics":{"Number of params":"35M","Test perplexity":"55.1","Validation perplexity":"57.3"},"paper_url":"https://arxiv.org/abs/1909.01792v2","paper_title":"Mogrifier LSTM","paper_date":"2019-09-04","code_links":[{"title":"deepmind/lamb","url":"https://github.com/deepmind/lamb"},{"title":"RMichaelSwan/MogrifierLSTM","url":"https://github.com/RMichaelSwan/MogrifierLSTM"},{"title":"microcoder-py/mogrifier-lstm","url":"https://github.com/microcoder-py/mogrifier-lstm"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33642,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-DOC + Partial Shuffle","metrics":{"Number of params":"37M","Test perplexity":"57.85","Validation perplexity":"60.16"},"paper_url":"http://arxiv.org/abs/1903.04167v2","paper_title":"Partially Shuffling the Training Data to Improve Language Models","paper_date":"2019-03-11","code_links":[{"title":"ofirpress/PartialShuffle","url":"https://github.com/ofirpress/PartialShuffle"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33643,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-DOC","metrics":{"Number of params":"37M","Test perplexity":"58.03","Validation perplexity":"60.29"},"paper_url":"http://arxiv.org/abs/1808.10143v2","paper_title":"Direct Output Connection for a High-Rank Language Model","paper_date":"2018-08-30","code_links":[{"title":"nttcslab-nlp/doc_lm","url":"https://github.com/nttcslab-nlp/doc_lm"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33644,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-MoS + Partial Shuffle","metrics":{"Number of params":"35M","Test perplexity":"59.98","Validation perplexity":"62.38"},"paper_url":"http://arxiv.org/abs/1903.04167v2","paper_title":"Partially Shuffling the Training Data to Improve Language Models","paper_date":"2019-03-11","code_links":[{"title":"ofirpress/PartialShuffle","url":"https://github.com/ofirpress/PartialShuffle"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33645,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-MoS","metrics":{"Number of params":"35M","Test perplexity":"61.45","Validation perplexity":"63.88"},"paper_url":"http://arxiv.org/abs/1711.03953v4","paper_title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","paper_date":"2017-11-10","code_links":[{"title":"zihangdai/mos","url":"https://github.com/zihangdai/mos"},{"title":"cstorm125/thai2fit","url":"https://github.com/cstorm125/thai2fit"},{"title":"tdmeeste/SparseSeqModels","url":"https://github.com/tdmeeste/SparseSeqModels"},{"title":"yfreedomliTHU/mos-pytorch1.1","url":"https://github.com/yfreedomliTHU/mos-pytorch1.1"},{"title":"nkcr/overlap-ml","url":"https://github.com/nkcr/overlap-ml"},{"title":"zhangyaoyuan/GAN-Simplification","url":"https://github.com/zhangyaoyuan/GAN-Simplification"},{"title":"nunezpaul/MNIST","url":"https://github.com/nunezpaul/MNIST"},{"title":"omerlux/Recurrent_Neural_Network_-_Part_2","url":"https://github.com/omerlux/Recurrent_Neural_Network_-_Part_2"},{"title":"omerlux/NLP-PTB","url":"https://github.com/omerlux/NLP-PTB"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33646,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-FWM Schlag et al. (2020)","metrics":{"Number of params":"37M","Test perplexity":"61.65","Validation perplexity":"54.48"},"paper_url":"https://arxiv.org/abs/2011.07831v2","paper_title":"Learning Associative Inference Using Fast Weight Memory","paper_date":"2020-11-16","code_links":[{"title":"ischlag/Fast-Weight-Memory-public","url":"https://github.com/ischlag/Fast-Weight-Memory-public"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33647,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM-DRILL","metrics":{"Number of params":"34M","Test perplexity":"61.9","Validation perplexity":"64.9"},"paper_url":"https://arxiv.org/abs/1905.05513v2","paper_title":"Deep Residual Output Layers for Neural Language Generation","paper_date":"2019-05-14","code_links":[{"title":"idiap/drill","url":"https://github.com/idiap/drill"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33648,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM 3-layer with Fraternal dropout","metrics":{"Number of params":"34M","Test perplexity":"64.1","Validation perplexity":"66.8"},"paper_url":"http://arxiv.org/abs/1711.00066v4","paper_title":"Fraternal Dropout","paper_date":"2017-10-31","code_links":[{"title":"kondiz/fraternal-dropout","url":"https://github.com/kondiz/fraternal-dropout"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33649,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM + ATOI","metrics":{"Number of params":"33M","Test perplexity":"64.73","Validation perplexity":"67.47"},"paper_url":"https://arxiv.org/abs/1909.08700v1","paper_title":"Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes","paper_date":"2019-09-18","code_links":[{"title":"nkcr/overlap-ml","url":"https://github.com/nkcr/overlap-ml"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33650,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"AWD-LSTM","metrics":{"Number of params":"33M","Test perplexity":"65.8","Validation perplexity":"68.6"},"paper_url":"http://arxiv.org/abs/1708.02182v1","paper_title":"Regularizing and Optimizing LSTM Language Models","paper_date":"2017-08-07","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/enas_lm"},{"title":"fastai/fastai","url":"https://github.com/fastai/fastai/blob/master/fastai/text/models/awdlstm.py"},{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"salesforce/awd-lstm-lm","url":"https://github.com/salesforce/awd-lstm-lm"},{"title":"castorini/hedwig","url":"https://github.com/castorini/hedwig"},{"title":"cstorm125/thai2fit","url":"https://github.com/cstorm125/thai2fit"},{"title":"castorini/Castor","url":"https://github.com/castorini/Castor"},{"title":"Han-JD/GRU-D","url":"https://github.com/Han-JD/GRU-D"},{"title":"iwangjian/ByteCup2018","url":"https://github.com/iwangjian/ByteCup2018"},{"title":"S-Abdelnabi/awt","url":"https://github.com/S-Abdelnabi/awt"},{"title":"Machine-Learning-Tokyo/Poetry-GAN","url":"https://github.com/Machine-Learning-Tokyo/Poetry-GAN"},{"title":"prajjwal1/language-modelling","url":"https://github.com/prajjwal1/language-modelling"},{"title":"AtheMathmo/AggMo","url":"https://github.com/AtheMathmo/AggMo"},{"title":"alexandra-chron/wassa-2018","url":"https://github.com/alexandra-chron/wassa-2018"},{"title":"alexandra-chron/ntua-slp-wassa-iest2018","url":"https://github.com/alexandra-chron/ntua-slp-wassa-iest2018"},{"title":"uclanlp/NamedEntityLanguageModel","url":"https://github.com/uclanlp/NamedEntityLanguageModel"},{"title":"mamamot/Russian-ULMFit","url":"https://github.com/mamamot/Russian-ULMFit"},{"title":"noise-field/Russian-ULMFit","url":"https://github.com/noise-field/Russian-ULMFit"},{"title":"Janus-Shiau/awd-lstm-tensorflow","url":"https://github.com/Janus-Shiau/awd-lstm-tensorflow"},{"title":"chris-tng/semi-supervised-nlp","url":"https://github.com/chris-tng/semi-supervised-nlp"},{"title":"ahmetumutdurmus/awd-lstm","url":"https://github.com/ahmetumutdurmus/awd-lstm"},{"title":"NightmareVoid/LSTM_for_EEG","url":"https://github.com/NightmareVoid/LSTM_for_EEG"},{"title":"jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"jb33k/awd-lstm-lm-ThinkNet","url":"https://github.com/jb33k/awd-lstm-lm-ThinkNet"},{"title":"rajs96/ULMFiT-Twitter-US-Airline-Sentiment","url":"https://github.com/rajs96/ULMFiT-Twitter-US-Airline-Sentiment"},{"title":"nkcr/overlap-ml","url":"https://github.com/nkcr/overlap-ml"},{"title":"jkkummerfeld/emnlp20lm","url":"https://github.com/jkkummerfeld/emnlp20lm"},{"title":"BenjiKCF/AWD-LSTM-sentiment-classifier","url":"https://github.com/BenjiKCF/AWD-LSTM-sentiment-classifier"},{"title":"mnhng/hier-char-emb","url":"https://github.com/mnhng/hier-char-emb"},{"title":"Amir-Hofo/Language_Modeling_with_LSTM_models","url":"https://github.com/Amir-Hofo/Language_Modeling_with_LSTM_models"},{"title":"SachinIchake/KALM","url":"https://github.com/SachinIchake/KALM"},{"title":"AtheMathmo/lookahead-lstm","url":"https://github.com/AtheMathmo/lookahead-lstm"},{"title":"llppff/ptb-lstmorqrnn-pytorch","url":"https://github.com/llppff/ptb-lstmorqrnn-pytorch"},{"title":"soyoung97/awd-lstm-gru","url":"https://github.com/soyoung97/awd-lstm-gru"},{"title":"Mees-Molenaar/protein_location","url":"https://github.com/Mees-Molenaar/protein_location"},{"title":"uchange/ulangel","url":"https://github.com/uchange/ulangel"},{"title":"vganesh46/awd-lstm-pytorch-implementation","url":"https://github.com/vganesh46/awd-lstm-pytorch-implementation"},{"title":"Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"arvieFrydenlund/awd-lstm-lm","url":"https://github.com/arvieFrydenlund/awd-lstm-lm"},{"title":"JessikaSmith/language_model","url":"https://github.com/JessikaSmith/language_model"},{"title":"ari-holtzman/genlm","url":"https://github.com/ari-holtzman/genlm"},{"title":"philippwirth/treelangrnn","url":"https://github.com/philippwirth/treelangrnn"},{"title":"varshinireddyt/ULMFiT","url":"https://github.com/varshinireddyt/ULMFiT"},{"title":"muellerzr/CodeFest_2019","url":"https://github.com/muellerzr/CodeFest_2019"},{"title":"philippwirth/awd-lstm-test","url":"https://github.com/philippwirth/awd-lstm-test"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33651,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Melis et al. (2017) - 1-layer LSTM (tied)","metrics":{"Number of params":"24M","Test perplexity":"65.9","Validation perplexity":"69.3"},"paper_url":"http://arxiv.org/abs/1707.05589v2","paper_title":"On the State of the Art of Evaluation in Neural Language Models","paper_date":"2017-07-18","code_links":[{"title":"deepmind/lamb","url":"https://github.com/deepmind/lamb"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33652,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Grave et al. (2016) - LSTM + continuous cache pointer","metrics":{"Test perplexity":"68.9"},"paper_url":"http://arxiv.org/abs/1612.04426v1","paper_title":"Improving Neural Language Models with a Continuous Cache","paper_date":"2016-12-13","code_links":[{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"salesforce/awd-lstm-lm","url":"https://github.com/salesforce/awd-lstm-lm"},{"title":"uclanlp/NamedEntityLanguageModel","url":"https://github.com/uclanlp/NamedEntityLanguageModel"},{"title":"jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"jb33k/awd-lstm-lm-ThinkNet","url":"https://github.com/jb33k/awd-lstm-lm-ThinkNet"},{"title":"SachinIchake/KALM","url":"https://github.com/SachinIchake/KALM"},{"title":"AtheMathmo/lookahead-lstm","url":"https://github.com/AtheMathmo/lookahead-lstm"},{"title":"philippwirth/treelangrnn","url":"https://github.com/philippwirth/treelangrnn"},{"title":"ari-holtzman/genlm","url":"https://github.com/ari-holtzman/genlm"},{"title":"arvieFrydenlund/awd-lstm-lm","url":"https://github.com/arvieFrydenlund/awd-lstm-lm"},{"title":"Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"soyoung97/awd-lstm-gru","url":"https://github.com/soyoung97/awd-lstm-gru"},{"title":"philippwirth/awd-lstm-test","url":"https://github.com/philippwirth/awd-lstm-test"},{"title":"llppff/ptb-lstmorqrnn-pytorch","url":"https://github.com/llppff/ptb-lstmorqrnn-pytorch"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33653,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"EGRU","metrics":{"Test perplexity":"68.9"},"paper_url":"https://arxiv.org/abs/2206.06178v3","paper_title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","paper_date":"2022-06-13","code_links":[{"title":"khaleelkhan/evnn","url":"https://github.com/khaleelkhan/evnn"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33654,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Inan et al. (2016) - Variational LSTM (tied) (h=650) + augmented loss","metrics":{"Test perplexity":"87.0","Validation perplexity":"91.5"},"paper_url":"http://arxiv.org/abs/1611.01462v3","paper_title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","paper_date":"2016-11-04","code_links":[{"title":"JianGoForIt/YellowFin_Pytorch","url":"https://github.com/JianGoForIt/YellowFin_Pytorch"},{"title":"rdspring1/PyTorch_GBW_LM","url":"https://github.com/rdspring1/PyTorch_GBW_LM"},{"title":"floydhub/word-language-model","url":"https://github.com/floydhub/word-language-model"},{"title":"InnerPeace-Wu/im2p-tensorflow","url":"https://github.com/InnerPeace-Wu/im2p-tensorflow"},{"title":"Ravoxsg/Word-level-language-modeling","url":"https://github.com/Ravoxsg/Word-level-language-modeling"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33655,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Inan et al. (2016) - Variational LSTM (tied) (h=650)","metrics":{"Test perplexity":"87.7","Validation perplexity":"92.3"},"paper_url":"http://arxiv.org/abs/1611.01462v3","paper_title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","paper_date":"2016-11-04","code_links":[{"title":"JianGoForIt/YellowFin_Pytorch","url":"https://github.com/JianGoForIt/YellowFin_Pytorch"},{"title":"rdspring1/PyTorch_GBW_LM","url":"https://github.com/rdspring1/PyTorch_GBW_LM"},{"title":"floydhub/word-language-model","url":"https://github.com/floydhub/word-language-model"},{"title":"InnerPeace-Wu/im2p-tensorflow","url":"https://github.com/InnerPeace-Wu/im2p-tensorflow"},{"title":"Ravoxsg/Word-level-language-modeling","url":"https://github.com/Ravoxsg/Word-level-language-modeling"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33656,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"Grave et al. (2016) - LSTM","metrics":{"Test perplexity":"99.3"},"paper_url":"http://arxiv.org/abs/1612.04426v1","paper_title":"Improving Neural Language Models with a Continuous Cache","paper_date":"2016-12-13","code_links":[{"title":"dmlc/gluon-nlp","url":"https://github.com/dmlc/gluon-nlp"},{"title":"salesforce/awd-lstm-lm","url":"https://github.com/salesforce/awd-lstm-lm"},{"title":"uclanlp/NamedEntityLanguageModel","url":"https://github.com/uclanlp/NamedEntityLanguageModel"},{"title":"jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/jhave/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"jb33k/awd-lstm-lm-ThinkNet","url":"https://github.com/jb33k/awd-lstm-lm-ThinkNet"},{"title":"SachinIchake/KALM","url":"https://github.com/SachinIchake/KALM"},{"title":"AtheMathmo/lookahead-lstm","url":"https://github.com/AtheMathmo/lookahead-lstm"},{"title":"philippwirth/treelangrnn","url":"https://github.com/philippwirth/treelangrnn"},{"title":"ari-holtzman/genlm","url":"https://github.com/ari-holtzman/genlm"},{"title":"arvieFrydenlund/awd-lstm-lm","url":"https://github.com/arvieFrydenlund/awd-lstm-lm"},{"title":"Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration","url":"https://github.com/Asteur/RERITES-AvgWeightDescentLSTM-PoetryGeneration"},{"title":"soyoung97/awd-lstm-gru","url":"https://github.com/soyoung97/awd-lstm-gru"},{"title":"philippwirth/awd-lstm-test","url":"https://github.com/philippwirth/awd-lstm-test"},{"title":"llppff/ptb-lstmorqrnn-pytorch","url":"https://github.com/llppff/ptb-lstmorqrnn-pytorch"}],"metrics_order":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33657,"task":"Language Modelling","parent_task":null,"dataset":"WikiText-2","model_name":"OPT-175B (50% Sparsity)","metrics":{"Test perplexity":"234.77"},"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":"[\"Test perplexity\", \"Validation perplexity\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]}]}