|
--- |
|
library_name: transformers |
|
license: llama3.1 |
|
datasets: |
|
- jondurbin/gutenberg-dpo-v0.1 |
|
- nbeerbower/gutenberg2-dpo |
|
- jondurbin/truthy-dpo-v0.1 |
|
- kyujinpy/orca_math_dpo |
|
- antiven0m/physical-reasoning-dpo |
|
base_model: |
|
- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated |
|
--- |
|
 |
|
|
|
# Llama3.1-Allades-8B |
|
|
|
Allades finetunes abliterated Llama 3.1 with 5 datasets to improve creative writing, reasoning, and roleplay. |
|
|
|
## Datasets |
|
|
|
- [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) |
|
- [nbeerbower/gutenberg2-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg2-dpo) |
|
- [jondurbin/truthy-dpo-v0.1](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1) |
|
- [kyujinpy/orca_math_dpo](https://huggingface.co/datasets/kyujinpy/orca_math_dpo) |
|
- [antiven0m/physical-reasoning-dpo](https://huggingface.co/datasets/antiven0m/physical-reasoning-dpo) |
|
|
|
## Training |
|
|
|
[ORPO tuned](https://mlabonne.github.io/blog/posts/2024-04-19_Fine_tune_Llama_3_with_ORPO.html) for 1 epoch with 2x RTX 3090 (sponsored by [Schneewolf Labs](https://schneewolflabs.com)). |
|
|
|
Data was prepared with [Llama 3.1 Instruct](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1/). |
