Self-Fulfilling (Mis)alignment: Post-Trained Models
Collection
Here is a selection of models that have undergone DPO. We also share the earlier instruction checkpoints. We recommend using the DPO models. • 22 items • Updated
• 1
Tim Farrelly
timf34
·
AI & ML interests
None yet
Recent Activity
liked
a dataset about 15 hours ago
Jozdien/realistic_reward_hacks upvoted a collection about 1 month ago
Self-Fulfilling (Mis)alignment: Post-Trained Models upvoted a collection about 1 month ago
Self-Fulfilling (Mis)alignment: Emergent Misalignment Organizations
None yet