inference about lora model
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
hi ,
I trained chatglm3 with lora, and when it was deployed on fastchat, it generated repeated answers, but the output was normal if I used transformers' built-in generate method.
fastchat output:
normal output:
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
Reproduce the reported difference between FastChat deployment and Transformers' built-in generate method using the ChatGLM3 LoRA model. Compare the generated outputs and isolate why FastChat produces repeated answers; done means deployed inference matches the normal generation behavior without repetition.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100