allenai/Dolci-Think-DPO-7B download history
allenai/Dolci-Think-DPO-7B is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 474 times (95 in the last 7 days), and 4,159 times in total. It ranks #34,542 among datasets by monthly downloads.
Dolci Think 7B DPO Mixture 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 7B DPO mixture was used to preference tune Olmo 3 Think 7B. It contains 150,000 preference pairs created w
Models trained on Dolci-Think-DPO-7B
6 models list it as training data.
- allenai/Olmo-3-7B-Instruct-DPO 15.1K downloads in 30 days
- allenai/Olmo-3-7B-Think-DPO 10.4K downloads in 30 days
- mradermacher/Olmo-3-7B-Instruct-DPO-i1-GGUF 1.3K downloads in 30 days
- mradermacher/Olmo-3-7B-Think-DPO-i1-GGUF 985 downloads in 30 days
- mradermacher/Olmo-3-7B-Instruct-DPO-GGUF 481 downloads in 30 days
- mradermacher/Olmo-3-7B-Think-DPO-GGUF 357 downloads in 30 days