This collection consists of the relevant models for the second assignment of the course CS60216: Safety Fundamentals for Generative AI.
Anirvan Krishna
anirvankrishna
·
AI & ML interests
Deep Learning, Computer Vision, Natural language Processing, Generative Models, Reinforcement Learning, Medical Image Analysis
Organizations
Parameter Space vs. Activation Space Interventions
This collection consists of the relevant models for the second assignment of the course CS60216: Safety Fundamentals for Generative AI.
A Comparative Analysis between RLHF PPO and DPO
This collection contains the relevant trained models for the first assignment of the course CS60216: Safety Fundamentals for Generative AI.
models 18
anirvankrishna/model_sft_lora_fused
Text Generation • 2B • Updated • 8 •
anirvankrishna/model_sft_resta_dare
Text Generation • 2B • Updated • 11
anirvankrishna/model_sft_resta
Text Generation • 2B • Updated • 8
anirvankrishna/model_delta_safe
Text Generation • 2B • Updated • 8
anirvankrishna/model_harmful_lora_fused
Text Generation • 2B • Updated • 7
anirvankrishna/model_harmful_lora
Updated
anirvankrishna/model_sft_dare
Text Generation • 2B • Updated • 10 •
anirvankrishna/model_sft_lora
Updated
anirvankrishna/TaskA_QLoRA_Finetune
Reinforcement Learning • Updated • 4
anirvankrishna/TaskB_Prefix_Finetune
Updated