PAIR-code / PAIR-code/deliberate-lab
Change available sampling parameters depending on API
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 96
- Forks
- 40
- Avg merge
- 2d 11h
- Merged PRs (30d)
- 20
Description
As of today, we have frequency penalty and presence penalty parameters that can be passed through to Gemini and OpenAI APIs, but they'll be ignored for Ollama. That could confuse experimenters. The confusion could get worse if we ever add support for more complicated parameters with less-broad support (e.g. mirostat, min p). Ideally we'd note which APIs support which parameters, and only display applicable ones.
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 controls that expose frequency and presence penalties, then trace how Gemini, OpenAI, and Ollama sampling parameters are represented. Check how the interface identifies the selected API and whether capability information already exists. Done means each sampling parameter is clearly marked or displayed only when supported by the selected API.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 50/100