ml-intern

개요

ML Intern은 Hugging Face 생태계를 활용하여 자율적으로 고품질 머신러닝 코드를 연구, 작성 및 게시하는 명령줄 도구로, 문서, 논문, 데이터셋 및 클라우드 컴퓨팅 리소스에 깊이 접근하며 대화형 및 자동 모드를 지원합니다.

README 미리보기

\n  \n\n\n\n    \n    \n\n\n# ML Intern\n\nAn ML intern that autonomously researches, writes, and ships good quality ML related code using the Hugging Face ecosystem — with deep access to docs, papers, datasets, and cloud compute.\n\n## Quick Start\n\n### Installation\n\n```bash\ngit clone git@github.com:huggingface/ml-intern.git\ncd ml-intern\nuv sync\nuv tool install -e .\n```\n\n#### That's it. Now `ml-intern` works from any directory:\n\n```bash\nml-intern\n```\n\nCreate a `.env` file in the project root (or export these in your shell):\n\n```bash\nANTHROPIC_API_KEY= # if using anthropic models\nOPENAI_API_KEY= # if using openai models\nLOCAL_LLM_BASE_URL=http://localhost:8000 # shared fallback for local model prefixes\nLOCAL_LLM_API_KEY= # optional shared local API key\nHF_TOKEN=\nGITHUB_TOKEN= \n```\nIf no `HF_TOKEN` is set, the CLI will prompt you to paste one on first launch\nunless you start on a local model. To get a GITHUB_TOKEN follow the tutorial\n[here](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens#creating-a-fine-grained-personal-access-token).\n\n### Usage\n\n**Interactive mode** (start a chat session):\n\n```bash\nml-intern\n```\n\n**Headless mode** (single prompt, auto-approve):\n\n```bash\nml-intern "fine-tune llama on my dataset"\n```\n\n**Options:**\n\n```bash\nml-intern --model anthropic/claude-opus-4-7 "your prompt"   # requires ANTHROPIC_API_KEY\nml-intern --model openai/gpt-5.5 "your prompt"              # requires OPENAI_API_KEY\nml-intern --model ollama/llama3.1:8b "your prompt"\nml-intern --model vllm/meta-llama/Llama-3.1-8B-Instruct "your prompt"\nml-intern --sandbox-tools "your prompt"                         # use HF Space sandbox tools\nml-intern --max-iterations 100 "your prompt"\nml-intern --no-stream "your prompt"\n```\n\nRun `ml-intern` then `/model` to see the full list of suggested model ids\n(Claude, GPT, HF-router models like MiniMax, Kimi, GLM, DeepSeek, an

FAQ (1)