qingy2024/PR2-SFT download history
qingy2024/PR2-SFT is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 18 times (3 in the last 7 days), and 635 times in total. It ranks #402,156 among datasets by monthly downloads.
PR2 SFT PR2 is a new experimental dataset to get reasoning models to plan before thinking before responding. Responses were generated with DeepSeek V3. Subset Explanation The PR2 dataset is divided into two subsets: verified: This subset has been verified using Qwen2.5 72B Ins
Models trained on PR2-SFT
3 models list it as training data.
- mradermacher/PR2-14B-Instruct-GGUF 209 downloads in 30 days
- qingy2024/PR2-14B-Instruct 7 downloads in 30 days
- qingy2024/PR2-14B-Instruct-LoRA – downloads in 30 days