michaelfeil / michaelfeil/infinity
Support for models trained with SetFit for classification
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 206
- PR merge metrics
- No merged PRs in 30d
Description
### Feature request
How can we use embedding models trained under setFit for classification using infinity.
### Motivation
https://github.com/huggingface/setfit
is a good library that allows fine tuning of embedding models for downstream tasks. Infinity server being the one stop solution for embeddings, it will be good have it supported.
### Your contribution
NA
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing Infinity's existing embedding-model serving path alongside the linked Hugging Face SetFit project. Define the supported SetFit classification workflow and its completion criteria before implementation; the issue names no files or tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- backend-api-design, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100