- Dataset
- https://huggingface.co/datasets/allenai/Dolci-Think-DPO-32B
- Author
- allenai (org)
- Likes
- 11
- Downloads (30 days)
- 290
- License
- odc-by
- Size
- 100K<n<1M
- Tasks
- —
- Modalities
- text
- Gated
- No
- Created
- 2025-11-20
- Last modified
- 2026-01-05
- Snapshot
- 2026-10-21
Hugging Face dataset · #823
allenai/Dolci-Think-DPO-32B
allenai/Dolci-Think-DPO-32B is #823 among listed Hugging Face datasets, with 11 likes. This dataset is licensed under ODC-BY. It is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines. The Dolci Think DPO mixture was used to preference tune Olmo 3 Think 32B. It contains 200,000 preference pairs created with the preference…