{"task":"Text Generation","dataset":"OpenWebText","metric_names":["eval_loss"],"rows":[{"id":28920,"task":"Text Generation","parent_task":null,"dataset":"OpenWebText","model_name":"GPT2-Hermite","metrics":{"eval_loss":"2.91"},"paper_url":"https://arxiv.org/abs/2502.01247v2","paper_title":"Polynomial, trigonometric, and tropical activations","paper_date":"2025-02-03","code_links":[{"title":"K-H-Ismail/torchortho","url":"https://github.com/K-H-Ismail/torchortho"}],"metrics_order":"[\"eval_loss\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":28921,"task":"Text Generation","parent_task":null,"dataset":"OpenWebText","model_name":"GPT2-81M-LOOP","metrics":{"eval_loss":"3.11"},"paper_url":"https://arxiv.org/abs/2409.14199v3","paper_title":"Loop Neural Networks for Parameter Sharing","paper_date":"2024-09-21","code_links":[],"metrics_order":"[\"eval_loss\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]},{"id":28922,"task":"Text Generation","parent_task":null,"dataset":"OpenWebText","model_name":"GPT2-124M","metrics":{"eval_loss":"3.12"},"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":"[\"eval_loss\"]","area":"Adversarial","uses_additional_data":0,"source":"archive","tags":[]}]}