{"id":31696644,"url":"https://github.com/uziellujan/dl-textgen-textclass","last_synced_at":"2025-10-08T17:10:25.061Z","repository":{"id":316938948,"uuid":"1065393042","full_name":"UzielLujan/DL-TextGen-TextClass","owner":"UzielLujan","description":"Deep learning project on practical implementation of text generation and text classification pipelines with PyTorch and Hugging Face using RNNs, LSTMs, GRUs, and Transformers.","archived":false,"fork":false,"pushed_at":"2025-10-05T00:35:14.000Z","size":296,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-05T02:41:32.051Z","etag":null,"topics":["deep-learning","gru","huggingface","language-models","lstm","nlp-machine-learning","pytorch","rnn","text-classification","text-generation","transformers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/UzielLujan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-27T16:27:04.000Z","updated_at":"2025-10-05T00:35:17.000Z","dependencies_parsed_at":"2025-09-27T19:05:36.665Z","dependency_job_id":"9a6f8f4b-39c1-4285-8911-839f1f9cf4cc","html_url":"https://github.com/UzielLujan/DL-TextGen-TextClass","commit_stats":null,"previous_names":["uziellujan/dl-textgen-textclass"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/UzielLujan/DL-TextGen-TextClass","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UzielLujan%2FDL-TextGen-TextClass","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UzielLujan%2FDL-TextGen-TextClass/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UzielLujan%2FDL-TextGen-TextClass/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UzielLujan%2FDL-TextGen-TextClass/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/UzielLujan","download_url":"https://codeload.github.com/UzielLujan/DL-TextGen-TextClass/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/UzielLujan%2FDL-TextGen-TextClass/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278981518,"owners_count":26079640,"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","gru","huggingface","language-models","lstm","nlp-machine-learning","pytorch","rnn","text-classification","text-generation","transformers"],"created_at":"2025-10-08T17:10:20.542Z","updated_at":"2025-10-08T17:10:25.055Z","avatar_url":"https://github.com/UzielLujan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DL-TextGen-TextClass\n\nDeep learning project on practical implementation of text generation and text classification pipelines with PyTorch and Hugging Face using RNNs, LSTMs, GRUs, and Transformers.\n\nEste repositorio contiene la **Tarea 2** del curso de maestría *Deep Learning para Procesamiento de Texto e Imágenes*.  \n\n## 📂 Estructura del proyecto\n\n```bash\nDL-TextGen-TextClass/\n├── PartA/ # Generación de letras de canciones\n│ ├── data/\n│ ├── src/\n│ ├── models/\n│ ├── results/\n│ ├── logs/\n│ ├── jobs/\n│ └── README_A.md\n│\n├── PartB/ # Clasificación de reseñas turísticas\n│ ├── data/\n│ ├── src/\n│ ├── models/\n│ ├── results/\n│ ├── logs/\n│ ├── jobs/\n│ └── README_B.md (pendiente)\n│\n├── requirements.txt\n├── environment.yml\n└── README.md\n```\n\n\n- `PartA/README_A.md`: instrucciones específicas para generación de texto.\n- `PartB/README_B.md`: instrucciones específicas para clasificación.\n\n## Cómo ejecutar\nEl proyecto está preparado para correrse tanto en local como en el clúster **Lab-SB (CIMAT)**.  \nEjemplo (Parte A, caracter-level RNN):\n```bash\ncd PartA\nsbatch jobs/run_char.sh char_rnn_1\n```\n\n📦 Dependencias\n\n- Python 3.11\n- PyTorch + CUDA\n- Transformers\n- Datasets\n- Accelerate\n- Scikit-learn\n- Matplotlib, Pandas, Numpy\n\nInstalar con:\n```bash\nconda env create -f jobs/environment.yml\n```\nResultados esperados\n\n- Perplejidad (PPL) en generación.\n- Accuracy y F1-score en clasificación.\n- Gráficas de curvas de entrenamiento, matrices de confusión y ejemplos de letras generadas.\n- Tablas comparativas de arquitecturas y tiempos de cómputo.\n\n## Autor\nUziel Isaí Lujan López — M.Sc. in Statistical Computing at CIMAT\n\n'uziel.lujan@cimat.mx'\n\n[LinkedIn](https://www.linkedin.com/in/uziel-lujan/) | [GitHub](https://github.com/UzielLujan)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuziellujan%2Fdl-textgen-textclass","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fuziellujan%2Fdl-textgen-textclass","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuziellujan%2Fdl-textgen-textclass/lists"}