How to support rope scaling automatically for LLama based model?
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
the rope scaling config are supported in transformers now, but not enabled auto.
https://huggingface.co/docs/transformers/main/en/model_doc/llama2
How to make it automatically support rope scaling in fschat?
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
Start with the linked Transformers Llama2 documentation, then locate FastChat's Llama model-loading entry point and compare how rope scaling configuration is passed through. Done means supported rope scaling settings are recognized automatically for Llama-based models without manual intervention, with the behavior verified on a representative model.
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
- 30/100