{"data":{"slug":"bigcode-project-starcoder2","name":"starcoder2","tagline":"Home of StarCoder2!","github_url":"https://github.com/bigcode-project/starcoder2","owner":"bigcode-project","repo":"starcoder2","owner_avatar_url":"https://avatars.githubusercontent.com/u/110470554?v=4","primary_language":"Python","stars":2081,"forks":199,"topics":[],"archived":false,"github_pushed_at":"2024-03-21T11:54:59+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/bigcode-project-starcoder2","markdown_url":"https://www.graphcanon.com/tools/bigcode-project-starcoder2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bigcode-project-starcoder2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bigcode-project-starcoder2","description":"Home of StarCoder2!","homepage_url":null,"license":"Apache-2.0","open_issues":20,"watchers":17,"ai_summary":"Starcoder2 is a code generation model that leverages transformers and bitsandbytes for training and deployment.","readme_excerpt":"## Installation\nFirst, we have to install all the libraries listed in `requirements.txt`\n```bash\npip install -r requirements.txt\n\n---\n\n# pip install git+https://github.com/huggingface/transformers.git # TODO: merge PR to main\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\ncheckpoint = \"bigcode/starcoder2-15b\"\ndevice = \"cuda\" # for GPU usage or \"cpu\" for CPU usage\n\ntokenizer = AutoTokenizer.from_pretrained(checkpoint)\n\n---\n\n# pip install accelerate\nimport torch\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\n\ncheckpoint = \"bigcode/starcoder2-15b\"\ntokenizer = AutoTokenizer.from_pretrained(checkpoint)\n\n---\n\n# pip install bitsandbytes accelerate\nfrom transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig","github_created_at":"2023-12-08T08:46:25+00:00","created_at":"2026-07-11T23:43:49.367433+00:00","updated_at":"2026-08-05T12:01:52.984958+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":"python","name":"python"}],"trust":{"provenance":{"is_fork":false,"github_id":729030266,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-05T12:01:52.164Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":867,"last_release_at":null},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:43:51.049Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-05T12:01:52.681Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-05T12:01:52.681Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-05T12:01:52.681Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The library and model can be used freely under Apache-2.0 licensing terms."},"requirements":{"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["Use Starcoder2 when you require a model that leverages the bitsandbytes library, which can enhance memory usage during both training and inference processes.","Opt for this tool if your current setup already includes Hugging Face's transformers framework since Starcoder2 builds upon it directly."],"when_not_to_use":["Avoid Starcoder2 if you need to work with non-Python environments or frameworks, as its implementation is Python-specific and may not be easily transferable.","If your project strictly avoids external dependencies that are not part of the transformers core package, Starcoder2 might not be suitable due to its additional reliance on bitsandbytes."],"source":"enrich:decision_facts","observed_at":"2026-07-17T04:18:57.460Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - The library and model can be used freely under Apache-2.0 licensing terms."},{"label":"Adopt for","value":"Starcoder2 is a code generation model using transformers and bitsandbytes for improved training efficiency."}]}}