The <eos> token randomly pops out during the inference, making the text generation stops early.
Open
Nobody has claimed this yet.
bug
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
Several people have reported having this issue for the v1.1 model, which wasn't a bug for the v1.0 one. Do you plan on fixing that in the future?
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 names only the v1.1 and v1.0 models and does not identify a file, entry point, or test. Start by locating the inference and stopping-token handling for both model versions, then reproduce the premature termination and add a regression test showing that normal generation does not stop early.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100