Ex0bit/GLM-4.7-PRISM
Text Generation
•
353B
•
Updated
•
3.09k
•
27
Abdur Rahman
AbdurRahman11
AI & ML interests
None yet
Recent Activity
liked
a model
about 1 month ago
Ex0bit/GLM-4.7-PRISM
liked
a model
about 1 month ago
Ex0bit/MiniMax-M2.1-PRISM
liked
a model
about 1 month ago
huihui-ai/Huihui-IQuest-Coder-V1-40B-Loop-Instruct-abliterated
Organizations
None yet
liked
4
models
about 1 month ago
liked
2
models
2 months ago
liked
2
models
3 months ago
liked
3
models
4 months ago
liked
5
models
6 months ago
huihui-ai/Huihui-GLM-4.5V-abliterated
Image-Text-to-Text
•
108B
•
Updated
•
83
•
16
huihui-ai/Huihui-Qwen3-Coder-480B-A35B-Instruct-abliterated-GGUF
Text Generation
•
480B
•
Updated
•
370
•
13
huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated
Text Generation
•
21B
•
Updated
•
15k
•
177
huihui-ai/Huihui-Qwen3-Coder-30B-A3B-Instruct-abliterated
Text Generation
•
31B
•
Updated
•
3.41k
•
30
huihui-ai/Huihui-Qwen3-30B-A3B-Instruct-2507-abliterated
Text Generation
•
31B
•
Updated
•
381
•
39
liked
a
model
11 months ago
reacted to
mlabonne's
post with 👍
11 months ago
Post
18657
✂️ AutoAbliteration
I made a Colab notebook to automatically abliterate models.
It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.
💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing
I made a Colab notebook to automatically abliterate models.
It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.
💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing
- 1 reply
reacted to
mlabonne's
post with 👍
11 months ago
Post
6573
✂️ Gemma 3 Abliterated
I noticed that Gemma 3 was much more resilient to refusal removal than other models like Qwen 2.5.
I experimented with different recipes and improved the abliteration technique I wrote about last year.
It's still experimental but the refusal rate is super low in my tests. Enjoy!
mlabonne/gemma-3-4b-it-abliterated
mlabonne/gemma-3-12b-it-abliterated
mlabonne/gemma-3-27b-it-abliterated
I noticed that Gemma 3 was much more resilient to refusal removal than other models like Qwen 2.5.
I experimented with different recipes and improved the abliteration technique I wrote about last year.
It's still experimental but the refusal rate is super low in my tests. Enjoy!
mlabonne/gemma-3-4b-it-abliterated
mlabonne/gemma-3-12b-it-abliterated
mlabonne/gemma-3-27b-it-abliterated
- 4 replies
liked
a
model
11 months ago