Apply a "chat" label to LLMs
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.9k
- Forks
- 152
- Avg merge
- 4h 14m
- Merged PRs (30d)
- 11
Description
We need a way to deterministically identify if an FLM model is a chat-capable LLM model. Right now, AFAIK, FLM only has labels for things like embedding and transcription models to indicate they are not chat models, but no explicit chat label.
We are adding the chat label to Lemonade here: https://github.com/lemonade-sdk/lemonade/pull/3099
This will make client development much easier.
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 searching the repository for the existing embedding and transcription labels and the model-label definitions. Add an explicit chat label for chat-capable LLM models, then verify that clients can deterministically distinguish chat models from embedding and transcription models using the relevant tests, if present.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- ai, machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100