AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset download history
AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 35 times (3 in the last 7 days), and 261 times in total. It ranks #242,743 among datasets by monthly downloads.
COMPASS LODO Policy-Aware SFT (7 Domains) This dataset contains 4,121 query–response pairs used for the Leave-One-Domain-Out (LODO) policy-aware supervised fine-tuning (SFT) experiment in the COMPASS paper: COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLM
Models trained on COMPASS-Policy-aware-SFT-Dataset
1 models list it as training data.
- AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA 22 downloads in 30 days
Open AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.