{"id":25365812,"url":"https://github.com/willguimont/transformers","last_synced_at":"2025-10-08T19:03:22.072Z","repository":{"id":159920825,"uuid":"618028666","full_name":"willGuimont/transformers","owner":"willGuimont","description":"Flexible transformer implementation for research","archived":false,"fork":false,"pushed_at":"2025-02-12T19:41:57.000Z","size":110,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-09-05T00:19:29.682Z","etag":null,"topics":["deep-learning","deep-neural-networks","learning","machine-learning","pytorch","transformer","transformer-architecture"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/willGuimont.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-03-23T15:51:47.000Z","updated_at":"2025-02-12T19:42:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"c8f93809-5586-4c11-8609-8bc1810e92dd","html_url":"https://github.com/willGuimont/transformers","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/willGuimont/transformers","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/willGuimont%2Ftransformers","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/willGuimont%2Ftransformers/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/willGuimont%2Ftransformers/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/willGuimont%2Ftransformers/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/willGuimont","download_url":"https://codeload.github.com/willGuimont/transformers/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/willGuimont%2Ftransformers/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000601,"owners_count":26082786,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","deep-neural-networks","learning","machine-learning","pytorch","transformer","transformer-architecture"],"created_at":"2025-02-14T23:50:38.405Z","updated_at":"2025-10-08T19:03:22.031Z","avatar_url":"https://github.com/willGuimont.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# transformers\n\nCollection of easy to understand transformer-based models in PyTorch.\nThe implementation is heavily commented and should be easy to follow.\n\n## Installation\n\n```bash\npip install git+https://github.com/willGuimont/transformers\n```\n\n## Implemented models\n\nGeneral:\n\n- Transformer (Vaswani et al., 2017)\n- Parallel Transformer (Dehghani et al., 2023)\n- PerceiverIO (Jaegle et al., 2022)\n\nPositional encoding:\n\n- Sinusoidal positional encoding\n- Relative positional encoding\n- Learnable positional encoding\n- Learnable Fourier positional encoding (Li, 2021)\n\nVision:\n\n- VisionTransformer (Dosovitskiy et al., 2021)\n\nNLP:\n\n- Simple character-level Transformer language model\n\n## Next steps\n\n- VICReg\n- Rotary positional encoding https://arxiv.org/pdf/2104.09864.pdf\n- Optimizing Deeper Transformers on Small Datasets (Xu et al., 2021)\n- Neural Machine Translation by Jointly Learning to Align and Translate (Bahdanau et al., 2016)\n- Universal Transformers [Paper](https://arxiv.org/abs/2310.07096)\n- Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles (Ryali et al., 2023)\n- Swin Transformer (Liu et al., 2021)\n- DINO: Emerging Properties in Self-Supervised Vision Transformers (Caron et al., 2021)\n- FlashAttention (Dao et al., 2022)\n- DETR (Carion et al., 2020)\n- Unlimiformer: Long-Range Transformers with Unlimited Length Input (Bertsch et al., 2023)\n- PointBERT (Yu et al., 2022)\n- Hydra Attention: Efficient Attention with Many Heads (Bolya et al., 2022)\n- Hyena Hierarchy: Towards Larger Convolutional Language Models (Poli et al., 2023)\n- Thinking Like Transformers (Weiss et al., 2021)\n- Long short-term memory (Schmidhuber, 1997)\n- Rethinking Positional Encoding in Language Pre-training (Ke et al., 2021)\n\n## Cite this repository\n\n```\n@software{Guimont-Martin_transformer_flexible_and_2023,\n    author = {Guimont-Martin, William},\n    month = {2},\n    title = {{transformer: flexible and easy to understand transformer models}},\n    version = {0.1.0},\n    year = {2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwillguimont%2Ftransformers","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwillguimont%2Ftransformers","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwillguimont%2Ftransformers/lists"}