Artem

kabachuha

kabachuha

AI & ML interests

deep learning, natural language processing, text2image, text2video, computer vision, fusion power

Recent Activity

liked a model about 13 hours ago

llmfan46/Qwen3.5-27B-ultimate-irrefusable-heretic

liked a model about 15 hours ago

llmfan46/Qwen3.5-9B-ultra-heretic

liked a model about 15 hours ago

llmfan46/Qwen3.5-9B-ultimate-irrefusable-heretic

View all activity

Organizations

liked a model about 13 hours ago

llmfan46/Qwen3.5-27B-ultimate-irrefusable-heretic

Image-Text-to-Text • 27B • Updated about 20 hours ago • 239 • 6

liked 2 models about 15 hours ago

llmfan46/Qwen3.5-9B-ultra-heretic

Image-Text-to-Text • 9B • Updated about 19 hours ago • 2

llmfan46/Qwen3.5-9B-ultimate-irrefusable-heretic

Image-Text-to-Text • 9B • Updated about 17 hours ago • 6

liked a model about 16 hours ago

gghfez/Qwen3.5-27b-control-vectors

Text Generation • 312k • Updated about 19 hours ago • 1

reacted to danielhanchen's post with 🤗 1 day ago

Post

3751

Qwen releases 4 new Qwen3.5 Small models: 0.8B • 2B • 4B • 9B!

Run Qwen3.5-0.8B, 2B and 4B on your phone. Run 9B on 6GB RAM.

The vision reasoning LLMs perform better than models 4x their size.

GGUFs to run: https://huggingface.co/collections/unsloth/qwen35

Guide: https://unsloth.ai/docs/models/qwen3.5

3 replies

New activity in MuXodious/Qwen3.5-27B-tainted-heresy 1 day ago

Have you tried multidirectional abliteration?

🤝 1

#1 opened 3 days ago by

kabachuha

New activity in Lightricks/LTX-2 2 days ago

Any ETA for the updates?

#52 opened 2 days ago by

kabachuha

replied to etemiz's post 3 days ago

Interesting, looks like it's somewhere in the middle. The refusal rates would be nice to have compared as well to get the refusals / performance ratio marked

liked a model 3 days ago