Lightricks/LTX-2.3-fp8
Image-to-Video • Updated
• 94.1k • 40
Artem
kabachuha
AI & ML interests
deep learning, natural language processing, text2image, text2video, computer vision, fusion power
Recent Activity
new activity
5 days ago
Lightricks/LTX-2.3:LoRA-Camera-Control new activity
7 days ago
DontPlanToEnd/UGI-Leaderboard:Eval request: p-e-w / gpt-oss-20b-heretic-ara-v3 new activity
7 days ago
jukofyork/creative-writing-control-vectors-v3.0:“The doom lies in yourself, not in your name.” Organizations
LoRA-Camera-Control
3
#15 opened 5 days ago
by
HK-wang
Eval request: p-e-w / gpt-oss-20b-heretic-ara-v3
❤️ 5
2
#583 opened 7 days ago
by
kabachuha
“The doom lies in yourself, not in your name.”
👀 7
363
#15 opened 6 months ago
by
jukofyork
liked 3 models 7 days ago
UGI Eval?
1
#1 opened 7 days ago
by
kabachuha
Any ETA for the updates?
3
#52 opened 11 days ago
by
kabachuha
reacted to MaziyarPanahi's post with 🔥 8 days ago
Post
4170
DNA, mRNA, proteins, AI. I spent the last year going deep into computational biology as an ML engineer. This is Part I of what I found. 🧬
In 2024, AlphaFold won the Nobel Prize in Chemistry.
By 2026, the open-source community had built alternatives that outperform it.
That's the story I find most interesting about protein AI right now. Not just the science (which is incredible), but the speed at which open-source caught up. Multiple teams, independently, reproduced and then exceeded AlphaFold 3's accuracy with permissive licenses. The field went from prediction to generation: we're not just modeling known proteins anymore, we're designing new ones.
I spent months mapping this landscape for ML engineers. What the architectures actually are (spoiler: transformers and diffusion models), which tools to use for what, and which ones you can actually ship commercially.
New post on the Hugging Face blog: https://huggingface.co/blog/MaziyarPanahi/protein-ai-landscape
Hope you all enjoy! 🤗
In 2024, AlphaFold won the Nobel Prize in Chemistry.
By 2026, the open-source community had built alternatives that outperform it.
That's the story I find most interesting about protein AI right now. Not just the science (which is incredible), but the speed at which open-source caught up. Multiple teams, independently, reproduced and then exceeded AlphaFold 3's accuracy with permissive licenses. The field went from prediction to generation: we're not just modeling known proteins anymore, we're designing new ones.
I spent months mapping this landscape for ML engineers. What the architectures actually are (spoiler: transformers and diffusion models), which tools to use for what, and which ones you can actually ship commercially.
New post on the Hugging Face blog: https://huggingface.co/blog/MaziyarPanahi/protein-ai-landscape
Hope you all enjoy! 🤗
- 2 replies
Does it work with multimodal?
1
#1 opened 8 days ago
by
BingoBird
liked 2 models 8 days ago
RIP
🤝 10
2
#44 opened 9 days ago
by
kabachuha
liked 2 models 9 days ago
reacted to danielhanchen's post with 🤗 10 days ago
Post
5195
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
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
- 5 replies
Have you tried multidirectional abliteration?
🤝 1
6
#1 opened 11 days ago
by
kabachuha
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 12 days ago
@etemiz Which heretic model did you use? Have you tried the new heretic method here: https://huggingface.co/llmfan46/Qwen3.5-27B-heretic-v2?