Hugging Face's logo

Orion-zhen
/
Athene-V2-Chat-abliterated-bnb-4bit

Text Generation
Safetensors
English
Chinese
qwen2
conversational
4-bit precision
bitsandbytes
Model card Files Community
2
Orion-zhen commited on
Commit
219872a
·
verified ·
1 Parent(s): 82730e9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -12
README.md CHANGED
@@ -7,16 +7,5 @@ base_model:
7
  - Nexusflow/Athene-V2-Chat
8
  pipeline_tag: text-generation
9
  ---
10
- Athene-V2-Chat-abliterated-bnb-4bit
11
 
12
- 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
13
-
14
- Please... give my repo a star if you find it helpful. I will do whatever you want...
15
-
16
- ---
17
-
18
- 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. 模型使用 bitsandbytes 量化为 4bit 格式以减少显存占用.
19
-
20
- 求你了, 给我的仓库一个 star 吧, 我什么都会做的.
21
-
22
- ![i-will-do-anything](i-will-do-anything.png)
 
7
  - Nexusflow/Athene-V2-Chat
8
  pipeline_tag: text-generation
9
  ---
 
10
 
11
+ The model seems corrupted. sad :(