---
license: apache-2.0
library_name: transformers
base_model:
- mistralai/Mistral-7B-Instruct-v0.2
datasets:
- jondurbin/gutenberg-dpo-v0.1
- nbeerbower/gutenberg2-dpo
---

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

# Mistral-Gutenberg-Doppel-7B-FFT

[mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 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).

This is a full finetune rather than my usual QLoRA tunes. Mostly for learning purposes.

### Method

[ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) with 4x A100 for 2 epochs.