r4dix m46na

radixm46's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked 3 models 10 days ago

Local-Novel-LLM-project/WabiSabi-V1.5-beta-GGUF

Text Generation • 7B • Updated Mar 18 • 96 • 2

Local-Novel-LLM-project/Qwen3.5-Hasutsubomi-9B

Image-Text-to-Text • 9B • Updated Apr 1 • 19 • 4

nvidia/Qwen3.6-27B-NVFP4

Text Generation • 18B • Updated 12 days ago • 941k • 349

liked a model 11 days ago

nvidia/Qwen3.6-35B-A3B-NVFP4

Text Generation • 19B • Updated about 1 month ago • 8.37M • 460

liked a model 30 days ago

MiniMaxAI/MiniMax-M3

Image-Text-to-Text • 427B • Updated 1 day ago • 267k • • 1.32k

liked a model 3 months ago

prism-ml/Bonsai-8B-mlx-1bit

Text Generation • 0.4B • Updated Apr 18 • 6.76k • 223

liked a model 11 months ago

bartowski/openai_gpt-oss-20b-GGUF-MXFP4-Experimental

Text Generation • 21B • Updated Aug 5, 2025 • 199 • 8

upvoted a collection 11 months ago

gpt-oss

Collection

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 456

liked 2 models 11 months ago

unsloth/gpt-oss-20b-GGUF

Text Generation • 21B • Updated Dec 19, 2025 • 480k • 733

openai/gpt-oss-20b

Text Generation • 22B • Updated Aug 26, 2025 • 7.27M • • 4.79k

liked 3 models about 1 year ago

Menlo/Jan-nano-gguf

Text Generation • 4B • Updated Jul 1, 2025 • 1.16k • 142

Menlo/Jan-nano

Text Generation • 4B • Updated Jul 4, 2025 • 845 • • 507

pfnet/plamo-2-translate

Translation • 10B • Updated Nov 5, 2025 • 6.77k • 123

liked 3 models over 1 year ago

Aratako/calm3-22b-RP-v2

Text Generation • 23B • Updated Sep 16, 2024 • 32 • 20

dartags/DanbotNL-2408-260M

0.3B • Updated Mar 24, 2025 • 2.17k • 23

Local-Novel-LLM-project/kagemusya-7B-v1

Text Generation • 7B • Updated Jul 4, 2024 • 16 • 7

reacted to mlabonne's post with 👍 over 1 year ago

view post

Post

6664

✂️ 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

See translation

• 

• 
• 
• 
• 4 replies

·

🚀

16

16

👍

11

11

😎

5

5

❤️

4

4

+

Reply

liked 3 models over 1 year ago

mradermacher/gemma3-4b-it-abliterated-i1-GGUF

4B • Updated Jun 10 • 303 • 5

mradermacher/QwQ-32B-abliterated-i1-GGUF

33B • Updated Mar 8, 2025 • 1.71k • 17

cyberagent/DeepSeek-R1-Distill-Qwen-14B-Japanese

Text Generation • 15B • Updated Jan 27, 2025 • 126 • • 94