{"data":{"slug":"flagai-open-aquila2","name":"Aquila2","tagline":"Official repository for Aquila2 series large language models by BAAI","github_url":"https://github.com/FlagAI-Open/Aquila2","owner":"FlagAI-Open","repo":"Aquila2","owner_avatar_url":"https://avatars.githubusercontent.com/u/109567851?v=4","primary_language":"Python","stars":445,"forks":32,"topics":["llm","llm-inference","llm-training"],"archived":false,"github_pushed_at":"2024-10-11T09:25:46+00:00","maintenance_label":"Dormant","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/flagai-open-aquila2","markdown_url":"https://www.graphcanon.com/tools/flagai-open-aquila2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/flagai-open-aquila2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=flagai-open-aquila2","description":"The official repo of Aquila2 series proposed by BAAI, including pretrained & chat large language models.","homepage_url":null,"license":null,"open_issues":2,"watchers":4,"ai_summary":"Provides pretrained and chat-capable large language models developed by Beijing Academy of Artificial Intelligence (BAAI).","readme_excerpt":"## Requirements\n\n* python 3.10 and above\n* pytorch 1.12 and above, 2.0 and above are recommended\n* transformers 4.32 and above\n* CUDA 11.4 and above are recommended (this is for GPU users, flash-attention users, etc.)\n<br><br>\n\n---\n\n### Using Docker Image\nFor the environment that meets these [requirements](https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-23-06.html), you can also set up the environment required for Aquila2 by directly downloading [the Docker TAR file](https://model.baai.ac.cn/model-detail/220118), then loading and running it.\nBecause of all already installed dependencies, in the container you just pull all sources [FlagAI](https://github.com/FlagAI-Open/FlagAI.git) and [Aquila2](https://github.com/FlagAI-Open/Aquila2.git) and include both paths int environment variable, like export PYTHONPATH=$FLAGAI_HOME:$AQUILA2_HOME:$PYTHONPATH.\n\nNow you can use <img src=\"assets/baai.png\" width=\"18\"/> BAAI Modelhub or 🤗 Transformers to run our model。\n\n---\n\n## License Agreement\n\nThe Aquila2 project is based on the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0); The Aquila2 series models are based on the [BAAI Aquila Model License Agreement](./assets/aquila_license.pdf). Specially the Aquila2 70B series models are based on the [BAAI Aquila 70B Model License Agreement](./assets/aquila2_70b_license.pdf).\n\n<br><br>","github_created_at":"2023-09-26T04:37:19+00:00","created_at":"2026-07-11T11:46:17.764845+00:00","updated_at":"2026-09-20T06:36:20.249178+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"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":"llm","name":"llm"},{"slug":"llm-inference","name":"llm-inference"},{"slug":"llm-training","name":"llm-training"}],"trust":{"provenance":{"is_fork":false,"github_id":696601819,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T03:45:57.906Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":708,"last_release_at":null,"stars_delta_30d":-1,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:46:18.902Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T03:45:59.155Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T03:45:59.155Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need specialized support from Beijing Academy of Artificial Intelligence","Research or rely on Chinese-language resources"],"when_not_to_use":["Require comprehensive API and documentation clarity","Preferring open source licensing details"],"source":"enrich:decision_facts","observed_at":"2026-07-15T10:07:34.405Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Official suite for Aquila2 series LLM by BAAI"},{"label":"License detail","value":"(unknown)"}]}}