mremila/on-policy-merging-bucket-2
19.6 MB
Marawan Gamal
mremila
·
AI & ML interests
None yet
Recent Activity
updated a collection 12 days ago
Tamper Resistance updated a model 12 days ago
mremila/z7b-wmdp-bio__5pp__unlearn-fft-npo-wd__relearn-fft upvoted an article 12 days ago
Deriving the PPO Loss from First PrinciplesOrganizations
models 23
mremila/z7b-wmdp-bio__5pp__unlearn-fft-npo-wd__relearn-fft
Text Generation • 7B • Updated • 23
mremila/z7b-wmdp-bio__5pp__unlearn-fft-npo-wd
Text Generation • 7B • Updated • 45
mremila/Qwen3.5-4B-CMO
Image-Text-to-Text • Updated • 4
mremila/Qwen3.6-27B-CMO
Image-Text-to-Text • Updated • 9
mremila/Qwen3.6-27B-mbpp-finetuned-non-deceptive
Image-Text-to-Text • Updated • 6
mremila/Qwen3.6-27B-mbpp-finetuned-deceptive
Image-Text-to-Text • Updated • 5
mremila/Qwen3.6-27B-mbpp-w-steered-alpha-1.0
Updated
mremila/Qwen3.6-27B-steered-alpha-1.0
Updated
mremila/Qwen3.6-27B-dpo-honest-e1-n50
Image-Text-to-Text • Updated • 4
mremila/Qwen3.6-27B-dpo-honest-e5-n50
Image-Text-to-Text • Updated • 5