|
--- |
|
license: cc-by-nc-4.0 |
|
library_name: transformers |
|
base_model: |
|
- Sao10K/MN-12B-Lyra-v4 |
|
datasets: |
|
- jondurbin/gutenberg-dpo-v0.1 |
|
- nbeerbower/gutenberg2-dpo |
|
--- |
|
 |
|
|
|
# Lyra4-Gutenberg-12B |
|
|
|
[Sao10K/MN-12B-Lyra-v4](https://huggingface.co/Sao10K/MN-12B-Lyra-v4) 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). |
|
|
|
Features an increased sequence length from Lyra4-Gutenberg-12. |
|
|
|
### Method |
|
|
|
[ORPO Finetuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) using 2x RTX 3090 for 3 epochs. |
|
|
|
Training data was formatted with ChatML. |
|
|
