AlphaUncommon
JIA-Lab-research/Step-DPO
Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"
- Owner
- JIA-Lab-research (organization)
- Stars
- Stars: 398
- Forks
- Forks: 17
- Language
- Python
- License
- None
- Created
- 2024
- Topics
- dpollmmathreasoning
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by JIA-Lab-research
All 58 repos by JIA-Lab-research- JIA-Lab-research/MGMStars: 3,323PythonRC
- JIA-Lab-research/LISAStars: 2,690PythonRC
- JIA-Lab-research/LongLoRAStars: 2,684PythonRC
- JIA-Lab-research/DreamOmni2Stars: 1,968PythonBeta
- JIA-Lab-research/ControlNeXtStars: 1,646PythonBeta
- JIA-Lab-research/SNR-Aware-Low-Light-EnhanceStars: 1,045PythonBeta
Nearby in Python
All Python repos- ekimetrics/adaptive-chunkingStars: 398PythonAlpha
- elliottdehn/open-jobsStars: 398PythonAlpha
- oxnw/ai-phoneStars: 398PythonAlpha
- rpm-software-management/titoStars: 398PythonAlpha
- jorgebastida/django-dajaxiceStars: 398PythonAlpha
- slashmili/jdatetimeStars: 398PythonAlpha