{"data":{"slug":"jiayi-pan-tinyzero","name":"TinyZero","tagline":"Minimal reproduction of DeepSeek R1-Zero","github_url":"https://github.com/Jiayi-Pan/TinyZero","owner":"Jiayi-Pan","repo":"TinyZero","owner_avatar_url":"https://avatars.githubusercontent.com/u/55055083?v=4","primary_language":"Python","stars":13192,"forks":1582,"topics":[],"archived":false,"github_pushed_at":"2026-02-27T05:42:07+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/jiayi-pan-tinyzero","markdown_url":"https://www.graphcanon.com/tools/jiayi-pan-tinyzero.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jiayi-pan-tinyzero","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jiayi-pan-tinyzero","description":"Minimal reproduction of DeepSeek R1-Zero","homepage_url":null,"license":"Apache-2.0","open_issues":82,"watchers":122,"ai_summary":"A minimal version of the R1-Zero architecture from DeepSeek, setup instructions provided in README for environment creation and dependencies installation including vLLM and Ray.","readme_excerpt":"## Installation\n\n```\nconda create -n zero python=3.9\n\n---\n\n# install torch [or you can skip this step and let vllm install the correct version for you]\npip install torch==2.4.0 --index-url https://download.pytorch.org/whl/cu121\n\n---\n\n# install vllm\npip3 install vllm==0.6.3 # or you can install 0.5.4, 0.4.2 and 0.3.1\npip3 install ray","github_created_at":"2025-01-21T16:49:12+00:00","created_at":"2026-07-11T10:30:02.506294+00:00","updated_at":"2026-07-12T07:43:56.597129+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"}],"tags":[{"slug":"deepseek","name":"deepseek"},{"slug":"r1-zero","name":"r1-zero"},{"slug":"ray","name":"ray"},{"slug":"vllm","name":"vllm"}],"trust":{"provenance":{"is_fork":false,"github_id":920152532,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-12T00:01:29.740Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":134,"last_release_at":null},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:30:04.044Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-12T00:01:33.373Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-12T00:01:33.373Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-12T00:01:33.373Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The framework itself is free and can be used without charge;"},"requirements":{"notes":["Specific Python environment setup (Python 3.9) and dependency installation steps are outlined in the README."],"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When you need a streamlined implementation of the R1-Zero architecture without unnecessary complexity.","For projects that require leveraging vLLM and Ray for efficient processing but prefer a lightweight framework setup."],"when_not_to_use":["If your project demands extensive customization options not available in this minimal version.","When working with environments where specific versions of PyTorch older than 2.4.0 are required, as TinyZero mandates the use of PyTorch 2.4.0 or allows vLLM to manage its installation."],"source":"enrich:decision_facts","observed_at":"2026-07-11T11:03:52.027Z"},"constraint_facets":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - The framework itself is free and can be used without charge;"},{"label":"Requirements","value":"Min 4 GB RAM; Specific Python environment setup (Python 3.9) and dependency installation steps are outlined in the README."},{"label":"Adopt for","value":"TinyZero is a scaled-down version of the R1-Zero architecture from DeepSeek, focusing on minimal setup with essential components."},{"label":"License detail","value":"TinyZero is licensed under Apache-2.0, allowing for broad usage with attribution requirements."}]}}