{"task":"Language Modelling","dataset":"Text8","metric_names":["Bit per Character (BPC)","Number of params"],"rows":[{"id":33481,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"GPT-2","metrics":{"Bit per Character (BPC)":"0.98","Number of params":"1542M"},"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":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33482,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Focus","metrics":{"Bit per Character (BPC)":"0.98","Number of params":"22M"},"paper_url":"https://arxiv.org/abs/2305.14952v2","paper_title":"Focus Your Attention (with Adaptive IIR Filters)","paper_date":"2023-05-24","code_links":[],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33483,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Transformer-XL + RMS dynamic eval + decay","metrics":{"Bit per Character (BPC)":"1.038","Number of params":"277M"},"paper_url":"http://arxiv.org/abs/1904.08378v1","paper_title":"Dynamic Evaluation of Transformer Language Models","paper_date":"2019-04-17","code_links":[{"title":"benkrause/dynamiceval-transformer","url":"https://github.com/benkrause/dynamiceval-transformer"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33484,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"24L Transformer + 8K adaptive span","metrics":{"Bit per Character (BPC)":"1.07","Number of params":"209M"},"paper_url":"https://arxiv.org/abs/1905.07799v2","paper_title":"Adaptive Attention Span in Transformers","paper_date":"2019-05-19","code_links":[{"title":"facebookresearch/adaptive-span","url":"https://github.com/facebookresearch/adaptive-span"},{"title":"jerrodparker20/adaptive-transformers-in-rl","url":"https://github.com/jerrodparker20/adaptive-transformers-in-rl"},{"title":"prajjwal1/fluence","url":"https://github.com/prajjwal1/fluence"},{"title":"lancopku/Explicit-Sparse-Transformer","url":"https://github.com/lancopku/Explicit-Sparse-Transformer"},{"title":"ofirpress/sandwich_transformer","url":"https://github.com/ofirpress/sandwich_transformer"},{"title":"prajjwal1/adaptive_transformer","url":"https://github.com/prajjwal1/adaptive_transformer"},{"title":"JoeRoussy/adaptive-attention-in-cv","url":"https://github.com/JoeRoussy/adaptive-attention-in-cv"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/7/Knowing-When-to-Look-Adaptive-Attention"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33485,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Transformer-XL - 24 layers","metrics":{"Bit per Character (BPC)":"1.08","Number of params":"277M"},"paper_url":"https://arxiv.org/abs/1901.02860v3","paper_title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","paper_date":"2019-01-09","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"NVIDIA/DeepLearningExamples","url":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/Transformer-XL"},{"title":"NVIDIA/DeepLearningExamples","url":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/LanguageModeling/Transformer-XL"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/transformer-xl"},{"title":"kimiyoung/transformer-xl","url":"https://github.com/kimiyoung/transformer-xl"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine"},{"title":"sooftware/conformer","url":"https://github.com/sooftware/conformer"},{"title":"mustafaaljadery/gemma-2b-10m","url":"https://github.com/mustafaaljadery/gemma-2b-10m"},{"title":"sooftware/nlp-attentions","url":"https://github.com/sooftware/nlp-attentions"},{"title":"sooftware/Attention-Implementation","url":"https://github.com/sooftware/Attention-Implementation"},{"title":"sooftware/attentions","url":"https://github.com/sooftware/attentions"},{"title":"sh951011/Attention-Implementation","url":"https://github.com/sh951011/Attention-Implementation"},{"title":"google-research/meliad","url":"https://github.com/google-research/meliad"},{"title":"shanghai-digital-brain-laboratory/bdm-db1","url":"https://github.com/shanghai-digital-brain-laboratory/bdm-db1"},{"title":"facebookresearch/code-prediction-transformer","url":"https://github.com/facebookresearch/code-prediction-transformer"},{"title":"okkteam/Transformer-Transducer","url":"https://github.com/okkteam/Transformer-Transducer"},{"title":"wxt1997/Transformer-Transducer","url":"https://github.com/wxt1997/Transformer-Transducer"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms"},{"title":"TimDettmers/transformer-xl","url":"https://github.com/TimDettmers/transformer-xl"},{"title":"inzva/fake-academic-paper-generation","url":"https://github.com/inzva/fake-academic-paper-generation"},{"title":"Machine-Learning-Tokyo/Poetry-GAN","url":"https://github.com/Machine-Learning-Tokyo/Poetry-GAN"},{"title":"benkrause/dynamiceval-transformer","url":"https://github.com/benkrause/dynamiceval-transformer"},{"title":"jincan333/lot","url":"https://github.com/jincan333/lot"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"aiha-lab/Attention-Head-Pruning","url":"https://github.com/aiha-lab/Attention-Head-Pruning"},{"title":"cedrickchee/pytorch-pretrained-BERT","url":"https://github.com/cedrickchee/pytorch-pretrained-BERT"},{"title":"park-cheol/ASR-Conformer","url":"https://github.com/park-cheol/ASR-Conformer"},{"title":"Jmkernes/PAR-Transformer-XL","url":"https://github.com/Jmkernes/PAR-Transformer-XL"},{"title":"zhdbwe/Paper-DailyReading","url":"https://github.com/zhdbwe/Paper-DailyReading"},{"title":"AIResearchHub/transformergallery","url":"https://github.com/AIResearchHub/transformergallery"},{"title":"cmunnis/BERT_vs_Transformer-XL","url":"https://github.com/cmunnis/BERT_vs_Transformer-XL"},{"title":"jiean001/models_m","url":"https://github.com/jiean001/models_m/tree/main/transformer_xl"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"},{"title":"2023-MindSpore-1/ms-code-220","url":"https://github.com/2023-MindSpore-1/ms-code-220/tree/main/transformer_xl"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33486,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"All-attention network - 36 layers","metrics":{"Bit per Character (BPC)":"1.08","Number of params":"114M"},"paper_url":"https://arxiv.org/abs/1907.01470v1","paper_title":"Augmenting Self-attention with Persistent Memory","paper_date":"2019-07-02","code_links":[{"title":"lucidrains/x-transformers","url":"https://github.com/lucidrains/x-transformers"},{"title":"facebookresearch/adaptive-span","url":"https://github.com/facebookresearch/adaptive-span"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33487,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Transformer-LS (small)","metrics":{"Bit per Character (BPC)":"1.09"},"paper_url":"https://arxiv.org/abs/2107.02192v3","paper_title":"Long-Short Transformer: Efficient Transformers for Language and Vision","paper_date":"2021-07-05","code_links":[{"title":"keonlee9420/Comprehensive-Transformer-TTS","url":"https://github.com/keonlee9420/Comprehensive-Transformer-TTS"},{"title":"NVIDIA/transformer-ls","url":"https://github.com/NVIDIA/transformer-ls"},{"title":"lucidrains/long-short-transformer","url":"https://github.com/lucidrains/long-short-transformer"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33488,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"12L Transformer + 8K adaptive span","metrics":{"Bit per Character (BPC)":"1.11","Number of params":"38M"},"paper_url":"https://arxiv.org/abs/1905.07799v2","paper_title":"Adaptive Attention Span in Transformers","paper_date":"2019-05-19","code_links":[{"title":"facebookresearch/adaptive-span","url":"https://github.com/facebookresearch/adaptive-span"},{"title":"jerrodparker20/adaptive-transformers-in-rl","url":"https://github.com/jerrodparker20/adaptive-transformers-in-rl"},{"title":"prajjwal1/fluence","url":"https://github.com/prajjwal1/fluence"},{"title":"lancopku/Explicit-Sparse-Transformer","url":"https://github.com/lancopku/Explicit-Sparse-Transformer"},{"title":"ofirpress/sandwich_transformer","url":"https://github.com/ofirpress/sandwich_transformer"},{"title":"prajjwal1/adaptive_transformer","url":"https://github.com/prajjwal1/adaptive_transformer"},{"title":"JoeRoussy/adaptive-attention-in-cv","url":"https://github.com/JoeRoussy/adaptive-attention-in-cv"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/7/Knowing-When-to-Look-Adaptive-Attention"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33489,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"All-attention network - 18 layers","metrics":{"Bit per Character (BPC)":"1.11","Number of params":"38M"},"paper_url":"https://arxiv.org/abs/1907.01470v1","paper_title":"Augmenting Self-attention with Persistent Memory","paper_date":"2019-07-02","code_links":[{"title":"lucidrains/x-transformers","url":"https://github.com/lucidrains/x-transformers"},{"title":"facebookresearch/adaptive-span","url":"https://github.com/facebookresearch/adaptive-span"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33490,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"BP-Transformer - 12 Layers","metrics":{"Bit per Character (BPC)":"1.11"},"paper_url":"https://arxiv.org/abs/1911.04070v1","paper_title":"BP-Transformer: Modelling Long-Range Context via Binary Partitioning","paper_date":"2019-11-11","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/transformer"},{"title":"yzh119/BPT","url":"https://github.com/yzh119/BPT"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33491,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"64-layer Character Transformer Model","metrics":{"Bit per Character (BPC)":"1.13","Number of params":"235M"},"paper_url":"http://arxiv.org/abs/1808.04444v2","paper_title":"Character-Level Language Modeling with Deeper Self-Attention","paper_date":"2018-08-09","code_links":[{"title":"facebookresearch/code-prediction-transformer","url":"https://github.com/facebookresearch/code-prediction-transformer"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33492,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"GAM-RHN-10","metrics":{"Bit per Character (BPC)":"1.157","Number of params":"44.7M"},"paper_url":"https://ieeexplore.ieee.org/document/8932404","paper_title":"Recurrent Highway Networks with Grouped Auxiliary Memory","paper_date":"2019-12-13","code_links":[{"title":"WilliamRo/gam_rhn","url":"https://github.com/WilliamRo/gam_rhn"},{"title":"MindCode-4/code-8","url":"https://github.com/MindCode-4/code-8/tree/main/recurrent-highway-network"},{"title":"MindSpore-scientific/code-5","url":"https://github.com/MindSpore-scientific/code-5/tree/main/recurrent-highway-network"},{"title":"MindCode-4/code-13","url":"https://github.com/MindCode-4/code-13/tree/main/recurrent-highway-network"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33493,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"12-layer Character Transformer Model","metrics":{"Bit per Character (BPC)":"1.18","Number of params":"44M"},"paper_url":"http://arxiv.org/abs/1808.04444v2","paper_title":"Character-Level Language Modeling with Deeper Self-Attention","paper_date":"2018-08-09","code_links":[{"title":"facebookresearch/code-prediction-transformer","url":"https://github.com/facebookresearch/code-prediction-transformer"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33494,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"PAR Transformer 24B","metrics":{"Bit per Character (BPC)":"1.18"},"paper_url":"https://arxiv.org/abs/2009.04534v3","paper_title":"Pay Attention when Required","paper_date":"2020-09-09","code_links":[{"title":"NVIDIA/DeepLearningExamples","url":"https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/LanguageModeling"},{"title":"Jmkernes/PAR-Transformer-XL","url":"https://github.com/Jmkernes/PAR-Transformer-XL"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33495,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"mLSTM + dynamic eval","metrics":{"Bit per Character (BPC)":"1.19","Number of params":"45M"},"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":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33496,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Bipartite flows (8 flows)","metrics":{"Bit per Character (BPC)":"1.23"},"paper_url":"https://arxiv.org/abs/1905.10347v1","paper_title":"Discrete Flows: Invertible Generative Models of Discrete Data","paper_date":"2019-05-24","code_links":[{"title":"google/edward2","url":"https://github.com/google/edward2"},{"title":"TrentBrick/PyTorchDiscreteFlows","url":"https://github.com/TrentBrick/PyTorchDiscreteFlows"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33497,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Large RHN","metrics":{"Bit per Character (BPC)":"1.27","Number of params":"46M"},"paper_url":"http://arxiv.org/abs/1607.03474v5","paper_title":"Recurrent Highway Networks","paper_date":"2016-07-12","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"julian121266/RecurrentHighwayNetworks","url":"https://github.com/julian121266/RecurrentHighwayNetworks"},{"title":"jzilly/RecurrentHighwayNetworks","url":"https://github.com/jzilly/RecurrentHighwayNetworks"},{"title":"vermaMachineLearning/Pytorch-JIT-Recurrent-Highway-Network","url":"https://github.com/vermaMachineLearning/Pytorch-JIT-Recurrent-Highway-Network"},{"title":"davidsvaughn/dts-tf","url":"https://github.com/davidsvaughn/dts-tf"},{"title":"nanzhaogang/contrib","url":"https://github.com/nanzhaogang/contrib/tree/master/application/recurrent-highway-network"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33498,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Large mLSTM +emb +WN +VD","metrics":{"Bit per Character (BPC)":"1.27","Number of params":"45M"},"paper_url":"http://arxiv.org/abs/1609.07959v3","paper_title":"Multiplicative LSTM for sequence modelling","paper_date":"2016-09-26","code_links":[{"title":"astakara48/python_project","url":"https://github.com/astakara48/python_project"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33499,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"LayerNorm HM-LSTM","metrics":{"Bit per Character (BPC)":"1.29","Number of params":"35M"},"paper_url":"http://arxiv.org/abs/1609.01704v7","paper_title":"Hierarchical Multiscale Recurrent Neural Networks","paper_date":"2016-09-06","code_links":[{"title":"bolducp/hierarchical-rnn","url":"https://github.com/bolducp/hierarchical-rnn"},{"title":"kaiu85/hm-rnn","url":"https://github.com/kaiu85/hm-rnn"},{"title":"nikolasthuesen/HMLSTM","url":"https://github.com/nikolasthuesen/HMLSTM"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33500,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"BN LSTM","metrics":{"Bit per Character (BPC)":"1.36","Number of params":"16M"},"paper_url":"http://arxiv.org/abs/1603.09025v5","paper_title":"Recurrent Batch Normalization","paper_date":"2016-03-30","code_links":[{"title":"cooijmanstim/recurrent-batch-normalization","url":"https://github.com/cooijmanstim/recurrent-batch-normalization"},{"title":"codedecde/Recognizing-Textual-Entailment","url":"https://github.com/codedecde/Recognizing-Textual-Entailment"},{"title":"Tetsuya-Nishikawa/ConvLSTM_DEMO","url":"https://github.com/Tetsuya-Nishikawa/ConvLSTM_DEMO"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33501,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"Unregularised mLSTM","metrics":{"Bit per Character (BPC)":"1.40","Number of params":"45M"},"paper_url":"http://arxiv.org/abs/1609.07959v3","paper_title":"Multiplicative LSTM for sequence modelling","paper_date":"2016-09-26","code_links":[{"title":"astakara48/python_project","url":"https://github.com/astakara48/python_project"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33502,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"BFN","metrics":{"Bit per Character (BPC)":"1.41"},"paper_url":"https://arxiv.org/abs/2308.07037v5","paper_title":"Bayesian Flow Networks","paper_date":"2023-08-14","code_links":[{"title":"nnaisense/bayesian-flow-networks","url":"https://github.com/nnaisense/bayesian-flow-networks"}],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33503,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"td-LSTM-large","metrics":{"Bit per Character (BPC)":"1.49"},"paper_url":"http://arxiv.org/abs/1602.08210v3","paper_title":"Architectural Complexity Measures of Recurrent Neural Networks","paper_date":"2016-02-26","code_links":[],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33504,"task":"Language Modelling","parent_task":null,"dataset":"Text8","model_name":"td-LSTM (Zhang et al., 2016)","metrics":{"Bit per Character (BPC)":"1.63"},"paper_url":"http://arxiv.org/abs/1602.08210v3","paper_title":"Architectural Complexity Measures of Recurrent Neural Networks","paper_date":"2016-02-26","code_links":[],"metrics_order":"[\"Bit per Character (BPC)\", \"Number of params\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]}]}