Adversarial Fine-tuning Interp

AI & ML interests

None defined yet.

Recent Activity

hanngao updated a model about 2 months ago

Adv-FT-Interp/qwen2.5-vl-7b-instruct-r1-s3-ft-ddp

hanngao published a model about 2 months ago

Adv-FT-Interp/qwen2.5-vl-7b-instruct-r1-s3-ft-ddp

hanngao updated a model about 2 months ago

Adv-FT-Interp/qwen3-vl-8b-instruct-r1-s3-ft-unnormalized-ddp

View all activity

models 21

Adv-FT-Interp/qwen2.5-vl-7b-instruct-r1-s3-ft-ddp

Adv-FT-Interp/qwen3-vl-8b-instruct-r1-s3-ft-unnormalized-ddp

Adv-FT-Interp/qwen3-vl-8b-instruct-r1-s3-ft-ddp

Adv-FT-Interp/qwen2.5-vl-7b-instruct-r1-s1-lambda1.0-clean-retention-ddp

Adv-FT-Interp/qwen2.5-vl-7b-instruct-r1-s3-lambda1.0-clean-retention-ddp

Adv-FT-Interp/qwen2.5-vl-7b-instruct-r1-s1-lambda0.1-clean-retention-ddp

Adv-FT-Interp/qwen2.5-vl-7b-instruct-r1-s3-clean-retention-ddp

Adv-FT-Interp/qwen3-vl-8b-instruct-r1-s3-clean-retention-ddp

Adv-FT-Interp/llava-1.5-7b-hf-s3-clean_retention-R1

Adv-FT-Interp/llava-1.5-7b-hf-s3-align-cls-preproj-R1

Feature Extraction • 0.3B • Updated Aug 22 • 3

datasets 0

None public yet