Commit
•
f5d5149
1
Parent(s):
e4dd938
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,4 +11,20 @@ base_model:
|
|
| 11 |
- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
|
| 12 |
---
|
| 13 |
|
| 14 |
-
# Llama3.1-Allades-8B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
- mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# Llama3.1-Allades-8B
|
| 15 |
+
|
| 16 |
+
Allades finetunes abliterated Llama 3.1 with 5 datasets to improve creative writing, reasoning, and roleplay.
|
| 17 |
+
|
| 18 |
+
## Datasets
|
| 19 |
+
|
| 20 |
+
- [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1)
|
| 21 |
+
- [nbeerbower/gutenberg2-dpo](https://huggingface.co/datasets/nbeerbower/gutenberg2-dpo)
|
| 22 |
+
- [jondurbin/truthy-dpo-v0.1](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1)
|
| 23 |
+
- [kyujinpy/orca_math_dpo](https://huggingface.co/datasets/kyujinpy/orca_math_dpo)
|
| 24 |
+
- [antiven0m/physical-reasoning-dpo](https://huggingface.co/datasets/antiven0m/physical-reasoning-dpo)
|
| 25 |
+
|
| 26 |
+
## Training
|
| 27 |
+
|
| 28 |
+
ORPO tuned for 1 epoch with 2x RTX 3090 (sponsored by [Schneewolf Labs](https://schneewolflabs.com)).
|
| 29 |
+
|
| 30 |
+
Data was prepared with [Llama 3.1 Instruct](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1/).
|