🤝 Open to Collab
Malikeh Ehghaghi
Malikeh1375
AI & ML interests
LLMs, AI Safety, Decentralized Training, Modular AI, Model Merging
Recent Activity
updated a collection 9 days ago
Abliterated Models liked a model 9 days ago
huihui-ai/Huihui-Qwen3.8-27B-abliterated upvoted a paper about 1 month ago
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning