Malikeh Ehghaghi

Malikeh1375's activity

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

updated a collection 17 days ago

Abliterated Models

Collection

1 item • Updated 17 days ago

liked a model 17 days ago

huihui-ai/Huihui-Qwen3.8-27B-abliterated

Image-Text-to-Text • 28B • Updated Aug 24 • 59.1k • • 488

upvoted a paper about 1 month ago

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Paper • 2403.03218 • Published Mar 5, 2024 • 3

upvoted 2 collections 2 months ago

✂️ Abliteration

Collection

Uncensored models using abliteration. See this article for more information: huggingface.co/blog/mlabonne/abliteration • 32 items • Updated Mar 2 • 173

Abliterated models

Collection

17 items • Updated May 6 • 7

upvoted an article 2 months ago

view article

Article

Uncensor any LLM with abliteration

• 

mlabonne

•

Jun 13, 2024

• 922

updated a collection 2 months ago

AI Safety Benchmarks

Collection

4 items • Updated Jul 17 • 1

liked a model 3 months ago

zai-org/GLM-5.2

Text Generation • 753B • Updated 27 days ago • 774k • • 5.14k

authored a paper 4 months ago

Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

Paper • 2606.11409 • Published Jun 9 • 10

upvoted a paper 4 months ago

Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

Paper • 2606.11409 • Published Jun 9 • 10

submitted a paper to Daily Papers 4 months ago

Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models

Paper • 2606.11409 • Published Jun 9 • 10

upvoted a collection 6 months ago

Qwen3Guard

Collection

7 items • Updated Dec 31, 2025 • 70

updated a collection 6 months ago

Safety-Aligned Models

Collection

17 items • Updated Apr 15