UNLamb FT Models
This repository aggregates finetuned benchmark models.
Models
| Model |
|---|
| Qwen2.5-7B-Instruct (PopQA FT) |
| Llama-3.1-8B-Instruct (PopQA FT) |
| Llama-3.2-3B-Instruct (PopQA FT) |
| Llama-3.2-1B-Instruct (PopQA FT) |
| gemma-7b-it (PopQA FT) |
Notes
- Checkpoints are uploaded from the local training outputs.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support