{"data":{"slug":"imoneoi-openchat","name":"openchat","tagline":"Advancing Open-source Language Models with Imperfect Data","github_url":"https://github.com/imoneoi/openchat","owner":"imoneoi","repo":"openchat","owner_avatar_url":"https://avatars.githubusercontent.com/u/26354659?v=4","primary_language":"Python","stars":5487,"forks":432,"topics":["large-language-models","open-source","transformers"],"archived":false,"github_pushed_at":"2024-09-13T07:46:22+00:00","maintenance_label":"Dormant","stars_delta_30d":2,"url":"https://www.graphcanon.com/tools/imoneoi-openchat","markdown_url":"https://www.graphcanon.com/tools/imoneoi-openchat.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/imoneoi-openchat","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=imoneoi-openchat","description":"OpenChat: Advancing Open-source Language Models with Imperfect Data","homepage_url":"https://openchat.team","license":"Apache-2.0","open_issues":137,"watchers":48,"ai_summary":"OpenChat is an open-source project focusing on advancing large language models using imperfect data, built on transformer architecture.","readme_excerpt":"# ⬇️ Installation\n> [!NOTE]\n> Need [`pytorch`](https://pytorch.org/get-started/locally/#start-locally) and [CUDA](https://developer.nvidia.com/cuda-toolkit-archive) to run OpenChat\n\n---\n\n# License\n\nCode is distributed under the **Apache License 2.0**.","github_created_at":"2023-05-25T14:58:59+00:00","created_at":"2026-07-07T17:34:56.914001+00:00","updated_at":"2026-08-17T12:01:19.908721+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"apache-license-2-0","name":"apache license 2.0"},{"slug":"cuda","name":"cuda"},{"slug":"large-language-models","name":"large language models"},{"slug":"open-source","name":"open-source"},{"slug":"pytorch","name":"pytorch"},{"slug":"transformers","name":"transformers"}],"trust":{"provenance":{"is_fork":false,"github_id":645397533,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-17T12:01:19.045Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":703,"last_release_at":"2024-05-24T18:26:23Z","stars_delta_30d":2,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:04:24.778Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-17T12:01:19.550Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-17T12:01:19.550Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-17T12:01:19.550Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need to train models on datasets with noise or missing information","Your project supports Apache License 2.0 and requires PyTorch, CUDA"],"when_not_to_use":["If your dataset is clean and well-structured, reducing model inaccuracies","Projects that cannot depend on Apache License 2.0 or install PyTorch with CUDA support"],"source":"enrich:decision_facts","observed_at":"2026-07-14T21:36:08.769Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"A Python library for training large language models with imperfect data using transformers."}]}}