Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: llama3.1
|
| 4 |
+
tags:
|
| 5 |
+
- autoquant
|
| 6 |
+
- gguf
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Meta-Llama-3.1-8B-Instruct-abliterated
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
This is an uncensored version of Llama 3.1 8B Instruct created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).
|
| 14 |
+
|
| 15 |
+
Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.
|
| 16 |
+
|
| 17 |
+
## ⚡️ Quantization
|
| 18 |
+
|
| 19 |
+
Thanks to ZeroWw and Apel-sin for the quants.
|
| 20 |
+
|
| 21 |
+
* **Better GGUF**: https://huggingface.co/ZeroWw/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF
|
| 22 |
+
* **EXL2**: https://huggingface.co/Apel-sin/llama-3.1-8B-abliterated-exl2
|