arxiv:2406.02575
Erfan Shayegani π
Erfan-Shayegani
AI & ML interests
AI Safety - Responsible AI - Large Multi-Modal Models
Recent Activity
upvoted
an
article
about 16 hours ago
Abliterating Refusal and CodeΒ LLMs
liked
a model
1 day ago
microsoft/Phi-3.5-vision-instruct
liked
a model
12 days ago
royokong/e5-v
Organizations
Papers
3
models
8
Erfan-Shayegani/llama2-lora_Unlearned_Accelerate_bad_weight_0.05
Updated
Erfan-Shayegani/llama2-lora_Unlearned_Accelerate_bad_weight_0.5
Updated
Erfan-Shayegani/llama2-lora_Unlearned_bad_weight_5e-1
Updated
Erfan-Shayegani/llama2-lora_Unlearned_bad_weight_5e-2
Updated
Erfan-Shayegani/llama2-lora_Unlearned
Updated
Erfan-Shayegani/opt-1.3b-lora_Unlearned
Updated
Erfan-Shayegani/GPTNeo-20b-lora
Updated
Erfan-Shayegani/opt-6.7b-lora
Updated
datasets
None public yet