{"data":{"slug":"qwenlm-qwen","name":"Qwen","tagline":"Official repo of Qwen, a large language model by Alibaba Cloud","github_url":"https://github.com/QwenLM/Qwen","owner":"QwenLM","repo":"Qwen","owner_avatar_url":"https://avatars.githubusercontent.com/u/141221163?v=4","primary_language":"Python","stars":21595,"forks":1872,"topics":["chinese","flash-attention","large-language-models","llm","natural-language-processing","pretrained-models"],"archived":false,"github_pushed_at":"2026-03-05T13:55:17+00:00","maintenance_label":"Slowing","stars_delta_30d":153,"url":"https://www.graphcanon.com/tools/qwenlm-qwen","markdown_url":"https://www.graphcanon.com/tools/qwenlm-qwen.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/qwenlm-qwen","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=qwenlm-qwen","description":"The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.","homepage_url":null,"license":"Apache-2.0","open_issues":44,"watchers":156,"ai_summary":"Provides the source code and deployment instructions for using Qwen, including pretrained models and utilities for flashing attention. Supports Python 3.8+, PyTorch, Transformers, and CUDA.","readme_excerpt":"## Requirements\n\n* python 3.8 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>\n\n---\n\n# pip install csrc/rotary\n```\n\nNow you can start with ModelScope or Transformers.\n\n---\n\n## 🐳 Docker\n\nTo simplify the deployment process, we provide docker images with pre-built environments: [qwenllm/qwen](https://hub.docker.com/r/qwenllm/qwen). You only need to install the driver and download model files to launch demos, deploy OpenAI API, and finetune the model.\n\n---\n\n# configure docker\nsudo systemctl start docker\n\n---\n\n# test if docker is correctly installed\nsudo docker run hello-world\n\n---\n\n### Deployment\n\nHere we use Qwen-7B-Chat as an example. Before launching a web demo or API, you can setup the configuration as shown below:\n\n```bash\nIMAGE_NAME=qwenllm/qwen:cu117\nPORT=8901\nCHECKPOINT_PATH=/path/to/Qwen-7B-Chat   # Path to downloaded model checkpoints and codes\n```\nThe following scripts can help you build:\n\n* OpenAI API\n```bash\nbash docker/docker_openai_api.sh -i ${IMAGE_NAME} -c ${CHECKPOINT_PATH} --port ${PORT}\n```\n\n* Web UI\n```bash\nbash docker/docker_web_demo.sh -i ${IMAGE_NAME} -c ${CHECKPOINT_PATH} --port ${PORT}\n```\n\n* CLI Demo\n```bash\nbash docker/docker_cli_demo.sh -i ${IMAGE_NAME} -c ${CHECKPOINT_PATH}\n```\n\nThe commands above will automatically download the required image and launch a Web UI demo in background (the service will auto-restart). You can open `http://localhost:${PORT}` on the host to use the demo.\n\nThe demo is successfully launched if you see the following output:\n\n```text\nSuccessfully started web demo. Open '...' to try!\nRun `docker logs ...` to check demo status.\nRun `docker rm -f ...` to stop and remove the demo.\n```\n\nIf you want to check the status of the demo, you can use `docker logs qwen` to display outputs.\n\nYou can use `docker rm -f qwen` to stop the service and remove the container.\n\n---\n\n## License Agreement\n\nThe source code provided at <https://github.com/QwenLM/Qwen> is licensed under the [Apache 2.0 License](./LICENSE) that can be found at the root directory.\n\nResearchers and developers are free to use the codes and model weights of both Qwen and Qwen-Chat. For their commercial use, please check the License Agreement accompanying each model.\n\n- Qwen-72B, Qwen-14B, and Qwen-7B are licensed under the [Tongyi Qianwen LICENSE AGREEMENT](./Tongyi%20Qianwen%20LICENSE%20AGREEMENT) that can be found at the corresponding HuggingFace and ModelScope repository. For commercial use, please fill out the form ([72B](https://dashscope.console.aliyun.com/openModelApply/Qwen-72B-Chat), [14B](https://dashscope.console.aliyun.com/openModelApply/Qwen-14B-Chat), and [7B](https://dashscope.console.aliyun.com/openModelApply/qianwen)) to apply.\n\n- Qwen-1.8B is licensed under the [Tongyi Qianwen RESEARCH LICENSE AGREEMENT](./Tongyi%20Qianwen%20RESEARCH%20LICENSE%20AGREEMENT) that can be found at the corresponding HuggingFace and ModelScope repository. For commercial use, please contact us.\n<br><br>","github_created_at":"2023-08-03T04:56:38+00:00","created_at":"2026-07-07T17:33:17.468764+00:00","updated_at":"2026-08-17T00:02:01.582055+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"}],"tags":[{"slug":"chinese","name":"chinese"},{"slug":"flash-attention","name":"flash-attention"},{"slug":"large-language-models","name":"large language models"},{"slug":"llm","name":"llm"},{"slug":"natural-language-processing","name":"natural-language-processing"},{"slug":"pretrained-models","name":"pretrained-models"}],"trust":{"provenance":{"is_fork":false,"github_id":674075444,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-17T00:02:00.821Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":164,"last_release_at":null,"stars_delta_30d":153,"open_issues_delta_30d":1},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":44,"high_count":0,"last_scan_at":"2026-07-11T11:00:36.542Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-17T00:02:01.285Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-17T00:02:01.285Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-17T00:02:01.285Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Python 3.8+","PyTorch 1.12+","Transformers 4.32+","CUDA 11.4+ (GPU users)"],"min_ram_gb":null},"constraints":{"min_ram_gb":null},"when_to_use":["If you are working with extensive Chinese text data, Qwen offers specialized capabilities that might not be found in other generic LLMs.","For applications requiring high-efficiency inference using flash-attention on GPU, Qwen provides optimized utilities and instructions for deployment."],"when_not_to_use":["If your project strictly requires a specific type of licensing, Qwen operates under the Apache-2.0 License with additional license agreements that may differ from general expectations and could pose a"],"source":"enrich:decision_facts","observed_at":"2026-07-11T14:08:57.896Z"},"constraint_facets":{"min_ram_gb":null},"decision_summary":[{"label":"Requirements","value":"Python 3.8+; PyTorch 1.12+; Transformers 4.32+; CUDA 11.4+ (GPU users)"},{"label":"Adopt for","value":"Qwen is a large language model by Alibaba Cloud with support for Chinese and advanced features like flash-attention."}]}}