About special tokens
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
When I use vllm and fastchat by chatglm3-6b, model always generate "assistant" special tokens, how can i fix it?
like:
"春风轻拂绿意新，|assistant|助时光荏苒。\n|assistant|勤勉不懈怠，|assistant|智慧照万方。"
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 by reproducing the output with vllm and FastChat using chatglm3-6b, then trace how special tokens are handled during generation. Done means the model no longer emits unintended "assistant" tokens in its response.
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