BetaRare
tatsu-lab/alpaca_farm
A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.
- Owner
- tatsu-lab (organization)
- Stars
- Stars: 844
- Forks
- Forks: 66
- Language
- Python
- License
- Apache-2.0
- Created
- 2023
- Topics
- deep-learninginstruction-followinglarge-language-modelsreinforcement-learning-from-human-feedbacknatural-language-processing
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by tatsu-lab
All 5 repos by tatsu-lab- tatsu-lab/stanford_alpacaStars: 30,231PythonLTS
- tatsu-lab/alpaca_evalStars: 2,023Jupyter NotebookRC
- tatsu-lab/gpt_paper_assistantStars: 552PythonAlpha
- tatsu-lab/opinions_qaStars: 124Jupyter NotebookPrototype
Nearby in Python
All Python repos- kandinskylab/kandinsky-5Stars: 844PythonBeta
- 3DTopia/4DNeXStars: 844PythonBeta
- VonHoltenCodes/SlowBooks-Pro-2026Stars: 844PythonBeta
- mpenning/ciscoconfparseStars: 844PythonBeta
- linkedin/irisStars: 844PythonBeta
- carnal0wnage/weirdAALStars: 844PythonBeta