Model Card for Model ID
This adapter for Gemma 7B has been fine-tuned (SFT) using unsloth on the instruction dataset HuggingFaceH4/deita-10k-v0-sft.
Model Details
The model was created using a recipe detailed in this article: Fine-tune a Better Google Gemma with Unsloth and Distilled DPO
- Developed by: The Kaitchup
- Model type: Causal
- Language(s) (NLP): English
- License: Apache 2.0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support