openai / openai/openai-openapi
suggestion on logprobs
Open
Nobody has claimed this yet.
api
enhancement
- Dominant language
- No language data
- Stars
- 2.5k
- Forks
- 527
- Avg merge
- 1h 46m
- Merged PRs (30d)
- 2
Description
hope can return logprobs of target token, such "yes" and "no"
very much can early stop and Engineering optimization
Forcing the model to output in a specific format that may increase hallucinations, can also reduce in many cases.
Contributor guide
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 locating the OpenAPI definitions for completion or chat token outputs and review how existing logprobs fields are represented. Determine which endpoint and response shape should expose target-token probabilities, then treat the work as complete when the proposed schema is documented with a valid example and passes the repository's specification checks.
Written by the indexing model from the issue text.
Assessment
- Domain
- api
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100