sail-sg / oat
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
Why this job: works in the areas we cover, but does not say which job it does
What it does
Oat 🌾 is a simple yet efficient framework for running online LLM alignment algorithms. Its key features include:
Get started
pip install vllm==0.8.4 && pip install -U oat-llm- Maintenance
- Inactive
- Last commit 9 months ago
- Stars
- 676
- +2 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.2.4
- Released 10 months ago
- Built with
- Python
- 97% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 63% closed
- 7 still open
- Pull requests
- 58 merged
- 2 waiting
- Releases
- 15
- 1 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| om-ai-lab / VLM-R1 | 6,045 | 4 months ago | Apache-2.0 | No downloads |
| agentscope-ai / Trinity-RFT | 714 | 35 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 97%
- Shell 2%
- Makefile <1%
Topics
- alignment
- dpo
- llm
- llm-aligment
- rlhf
- thompson-sampling
- online-alignment
- dueling-bandits
- distributed-training
- distributed-rl
- llm-exploration
- online-rl
Project record
- JobOther AI tools
- StatusListed
- Commits69
- Forks64
- Watching8
- Stars in 28 days+3
- CreatedOct 15, 2024
- First seen by usNov 7, 2026
- CheckedNov 8, 2026