Ducati Murati

directionallyverygood

AI & ML interests

Using LLMs for Learning, Conversational Reasoning, and Professional Image Editing has reignited my love for computing, so here we are.

Recent Activity

upvoted a collection 5 days ago

RealVisXL (SDXL)

liked a model 5 days ago

Shinku/lora-anima-1.0

upvoted an article 6 days ago

AI Agents List [2026] | Frameworks, Agentic Harnesses & Useful Repos

View all activity

Organizations

None yet

upvoted a collection 5 days ago

RealVisXL (SDXL)

Collection

12 items • Updated Mar 2 • 87

upvoted an article 6 days ago

Article

AI Agents List [2026] | Frameworks, Agentic Harnesses & Useful Repos

tegridydev

•

7 days ago

• 5

upvoted an article 15 days ago

Article

What If the Adaptation Were a Model? ShadowPEFT in 🤗 PEFT library

shadow-llm

•

16 days ago

• 24

upvoted 2 collections 29 days ago

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Collection

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 137 items • Updated 14 days ago • 170

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Collection

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes. • 45 items • Updated 20 days ago • 72

upvoted an article 2 months ago

Article

Welcome Inkling by Thinking Machines

burtenshaw, merve, pcuenq, ariG23498, andito

•

Jul 15

• 167

Ducati Murati

AI & ML interests

Recent Activity

Organizations

directionallyverygood's activity

AI Agents List [2026] | Frameworks, Agentic Harnesses & Useful Repos

What If the Adaptation Were a Model? ShadowPEFT in 🤗 PEFT library

Welcome Inkling by Thinking Machines