whitecircle / halo
Halo is an open-source framework built by White Circle for training large language and multimodal models
Why this job: topics: fine-tuning, lora, rlhf, reinforcement-learning, peft
What it does
Halo is an open-source framework built by White Circle for training large language and multimodal models. It supports pre-training, SFT, preference optimization, fully asynchronous multi-turn RL, and much more.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 853
- +14 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.2.0
- Released 6 days ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 39% closed
- 19 still open
- Pull requests
- 85 merged
- 9 waiting
- Releases
- 4
- 4 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| hiyouga / LlamaFactory | 75,965 | yesterday | Apache-2.0 | No downloads |
| huggingface / peft | 21,880 | today | Apache-2.0 | No downloads |
| MakazhanAlpamys / Soup | 10,385 | yesterday | Apache-2.0 | No downloads |
More: languages, topics, project record and preview image
Languages
- Python 99%
- Jinja <1%
- Makefile <1%
- Dockerfile <1%
Topics
- agent
- async-rl
- distributed-training
- fine-tuning
- grpo
- large-language-models
- llm
- lora
- model-parallelism
- moe
- multimodal
- peft
Project record
- JobFine-tuning
- StatusListed
- Commits64
- Forks45
- Watching3
- Stars in 28 days+34
- CreatedAug 26, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026