Finetune fastchat with Zephyr format
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
How can I perform fine-tuning on FastChat using the Zephyr format? I've noticed that within the preprocess function, there is hardcoded logic intended for fine-tuning with the Vicuna template.
Contributor guide
No contributing guide indexed for this repository
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
The issue points to the preprocess function but names no file or test. Start by locating that function and reviewing the existing Vicuna-specific fine-tuning logic alongside the requested Zephyr format; done means FastChat can fine-tune using Zephyr-format data. No test or entry point is named, so the relevant validation will need to be identified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100