Commit
•
2d6750b
1
Parent(s):
757e1f6
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.3
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
base_model:
|
| 7 |
+
- meta-llama/Llama-3.3-70B-Instruct
|
| 8 |
+
pipeline_tag: text-generation
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Llama-3.3-70B-Instruct-abliterated
|
| 12 |
+
|
| 13 |
+
Made with [Orion-zhen/abliteration](https://github.com/Orion-zhen/abliteration). The model is converted to 4bit by bitsandbytes to reduce VRAM usage. I'm too poor to rent a cloud server TAT
|
| 14 |
+
|
| 15 |
+
Please... give my repo a star if you find it helpful. I will do whatever you want...
|
| 16 |
+
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
使用 [Orion-zhen/abliteration](https://github.com/Orion-zhen/abliteration) 进行的 abliteration 操作. 校准集中包含中文, 可以减少对模型中文能力的损害.
|
| 20 |
+
|
| 21 |
+
求你了, 给我的仓库一个 star 吧, 我什么都会做的...
|
| 22 |
+
|
| 23 |
+
|