{"data":{"slug":"zai-org-codegeex","name":"CodeGeeX","tagline":"CodeGeeX: An Open Multilingual Code Generation Model","github_url":"https://github.com/zai-org/CodeGeeX","owner":"zai-org","repo":"CodeGeeX","owner_avatar_url":"https://avatars.githubusercontent.com/u/223098841?v=4","primary_language":"Python","stars":8806,"forks":686,"topics":["code-generation","pretrained-models","tools"],"archived":false,"github_pushed_at":"2024-08-13T05:59:38+00:00","maintenance_label":"Dormant","stars_delta_30d":-3,"url":"https://www.graphcanon.com/tools/zai-org-codegeex","markdown_url":"https://www.graphcanon.com/tools/zai-org-codegeex.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zai-org-codegeex","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zai-org-codegeex","description":"CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)","homepage_url":"https://codegeex.cn","license":"Apache-2.0","open_issues":189,"watchers":91,"ai_summary":"CodeGeeX is an open-source multilingual code generation model initially implemented in Mindspore and trained on Ascend 910 AI Processors. It offers a torch-compatible version for GPU platforms.","readme_excerpt":"## Getting Started\n\nCodeGeeX is initially implemented in Mindspore and trained Ascend 910 AI Processors. We provide a torch-compatible version based on [Megatron-LM](https://github.com/NVIDIA/Megatron-LM) to facilitate usage on GPU platforms.\n\n---\n\n### Installation\n\nPython 3.7+ / CUDA 11+ / PyTorch 1.10+ / DeepSpeed 0.6+ are required. Install ``codegeex`` package via: \n```bash\ngit clone git@github.com:THUDM/CodeGeeX.git\ncd CodeGeeX\npip install -e .\n```\nOr use [CodeGeeX docker](https://hub.docker.com/r/codegeex/codegeex) to quickly set up the environment (with [nvidia-docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker) installed):\n```bash\ndocker pull codegeex/codegeex:latest\n\n---\n\n## License\n\nOur code is licensed under the [Apache-2.0 license](LICENSE).\nOur model is licensed under the [license](MODEL_LICENSE).","github_created_at":"2022-09-17T14:06:29+00:00","created_at":"2026-07-11T23:20:04.651215+00:00","updated_at":"2026-09-20T04:31:32.744546+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":"code-generation","name":"code-generation"},{"slug":"code-generation-model","name":"code-generation-model"},{"slug":"gpu-support","name":"gpu-support"},{"slug":"mindspore","name":"mindspore"},{"slug":"multilingual","name":"multilingual"},{"slug":"pretrained-models","name":"pretrained-models"},{"slug":"tools","name":"tools"},{"slug":"torch-compatible","name":"torch-compatible"}],"trust":{"provenance":{"is_fork":false,"github_id":537827151,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:32:30.871Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":766,"last_release_at":null,"stars_delta_30d":-3,"open_issues_delta_30d":1},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":94,"high_count":0,"last_scan_at":"2026-09-18T08:32:33.113Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:32:29.652Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:32:29.652Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:32:29.652Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Requires Python 3.7+, CUDA 11+, PyTorch 1.10+, and DeepSpeed 0.6+.","Supports installation via pip or through a Docker container for quick setup."],"min_ram_gb":null,"requires_docker":true},"constraints":{"min_ram_gb":null,"requires_docker":true},"when_to_use":["When you need a multilingual code generation model that supports both Mindspore and PyTorch frameworks, allowing flexibility between Ascend 910 AI Processors and GPU platforms.","If your project requires an open-source solution under the Apache-2.0 license, ensuring freedom to use, modify, and distribute the code.","When you are working in an environment that requires deep integration with NVIDIA's Megatron-LM for GPU support, as CodeGeeX provides a torch-compatible version based on this framework."],"when_not_to_use":["If your project is strictly limited to TensorFlow or other frameworks not supported by CodeGeeX, as it primarily supports Mindspore and PyTorch.","When your development environment does not support Python 3.7+, CUDA 11+, PyTorch 1.10+, or DeepSpeed 0.6+, as these are the minimum requirements for running CodeGeeX.","If you are looking for a model that does not require specific hardware like Ascend 910 AI Processors or GPUs, as CodeGeeX is optimized for these platforms."],"source":"enrich:decision_facts","observed_at":"2026-09-18T10:26:49.139Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Requires Docker; Requires Python 3.7+, CUDA 11+, PyTorch 1.10+, and DeepSpeed 0.6+.; Supports installation via pip or through a Docker container for quick setup."},{"label":"Adopt for","value":"CodeGeeX is an open-source multilingual code generation model that supports both Mindspore and PyTorch frameworks, making it suitable for developers working with Ascend 910 AI Processors or GPU platforms."},{"label":"License detail","value":"CodeGeeX is licensed under the Apache-2.0 license, allowing for broad use, modification, and distribution of the code, while the model itself is under a separate license."}]}}