22 lines
895 B
Markdown
22 lines
895 B
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
license_name: mrl
|
||
|
|
license_link: https://mistral.ai/licenses/MRL-0.1.md
|
||
|
|
library_name: transformers
|
||
|
|
base_model:
|
||
|
|
- mistralai/Mistral-Small-Instruct-2409
|
||
|
|
datasets:
|
||
|
|
- jondurbin/gutenberg-dpo-v0.1
|
||
|
|
- nbeerbower/gutenberg2-dpo
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
# Mistral-Small-Gutenberg-Doppel-22B
|
||
|
|
|
||
|
|
[mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409) 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 with an A40 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)
|