README.md

---
license: gemma
library_name: transformers
base_model:
- google/gemma-2-27b-it
datasets:
- jondurbin/gutenberg-dpo-v0.1
---
![image/png](https://huggingface.co/nbeerbower/gemma2-gutenberg-27B/resolve/main/gutenberg2-header.png?download=true)

# gemma2-gutenberg-27B

[google/gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it) finetuned on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1).

### Method

ORPO tuned with an 80GB A100 on RunPod (plz sponsor me) for 3 epochs.

[Fine-tune Llama 3 with ORPO](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html)