README.md

---
license: apache-2.0
library_name: transformers
base_model:
- Qwen/Qwen2.5-32B-Instruct
datasets:
- jondurbin/gutenberg-dpo-v0.1
- nbeerbower/gutenberg2-dpo
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
---

![image/png](https://huggingface.co/nbeerbower/Mistral-Small-Gutenberg-Doppel-22B/resolve/main/doppel-header?download=true)

# Qwen2.5-Gutenberg-Doppel-32B

[Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) finetuned on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) and [nbeerbower/gutenberg2-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg2-dpo).

### Method

[ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 2x A100 for 1.25 epochs.