How to train a router?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5.5k
- Forks
- 433
- PR merge metrics
- No merged PRs in 30d
Description
My understanding is that the current implementation of llm-router supports only these models?
strong_model="gpt-4-1106-preview",
weak_model="anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1",
Is that correct? The routellm/calibrate_threshold.py is just reading this dataset: https://huggingface.co/datasets/routellm/lmsys-arena-human-preference-55k-thresholds
How do I train a router to pick between these two models in Bedrock:
strong_model="meta.llama3-1-8b-instruct-v1:0",
weak_model="meta.llama3-1-405b-instruct-v1:0",
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 with routellm/calibrate_threshold.py and the linked lmsys-arena-human-preference-55k-thresholds dataset, then determine whether the current training flow supports the two Bedrock model identifiers. Done means documenting a reproducible way to train or calibrate a router for those models, or clearly stating the limitation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- aws, python
- Domain
- cloud, documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100