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
• 2
Boyd Kane
beyarkay
AI & ML interests
None yet
Recent Activity
upvoted a collection 3 days ago
Self-Fulfilling (Mis)alignment: Post-Trained Models updated
a dataset 12 days ago
beyarkay/elicitation-on-hard-wrapped-text published
a dataset 12 days ago
beyarkay/elicitation-on-hard-wrapped-text Organizations
None yet
upvoted a collection 3 days ago