camilablank's picture
Upload README.md with huggingface_hub
d3d4639 verified
|
Raw
History Blame Contribute Delete
341 Bytes
---
license: apache-2.0
tags:
- olmo
- dpo
- sycophancy
---
# OLMo-3 DPO delta-learning checkpoints
Preference-trained OLMo-3 checkpoints from size-pair / swapped delta-learning DPO experiments (sycophancy-confidence).
Each top-level folder is one training run (HF `transformers`-loadable weights, plus `step_500` DeepSpeed state).