Sophie Xhonneux's picture

Sophie Xhonneux

sophiex

·

AI & ML interests

LLM alignment and adversarial attacks/robustness

Organizations

sophiex 's models 7

sophiex/SFT-ATTACK

sophiex/onlinedpo_pythia2.8b_tldr6.9

3B • Updated Sep 30, 2024 • 4

sophiex/dpo_pythia1b_hh_rlhf.yml_local_29-04-24_13-31-33_xxxxx

Updated Apr 29, 2024 • 1

sophiex/dpo_pythia1b_hh_rlhf.yml_local_27-04-24_21-57-03_xxxxx

Updated Apr 28, 2024

sophiex/config_name_xxxxx

Updated Apr 27, 2024

sophiex/pythia-1b-sft_hh_rlhf

Text Generation • 1B • Updated Apr 27, 2024 • 8

sophiex/pythia-410m-sft_hh_rlhf

Updated Apr 26, 2024