LAION-AI / LAION-AI/Open-Assistant
Evaluate Microsoft DeepSpeed-Chat Training System
Open
Nobody has claimed this yet.
ml
- Dominant language
- Python
- Stars
- 37.4k
- Forks
- 3.3k
- PR merge metrics
- No merged PRs in 30d
Description
We are currently using CarperAI/trlx for our RL training and we are quite happy with it.
Today a RLHF DeepSpeed-Chat example was published for DeepSpeed. We should evaluate what the Microsoft solution offers and how it compares to other alternatives like trlx.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the linked DeepSpeed-Chat README, then compare its RLHF training workflow with the project's current CarperAI/trlx setup. Define comparison criteria and record whether DeepSpeed-Chat is a suitable alternative; the issue is done when the trade-offs and recommendation are documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100