SI-Lab/StepCountQA-SFT download history
SI-Lab/StepCountQA-SFT is a visual question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 462 times (30 in the last 7 days), and 4,699 times in total. It ranks #35,250 among datasets by monthly downloads.
StepCountQA-SFT StepCountQA-SFT is a multimodal supervised fine-tuning (SFT) dataset for visual object counting with step-by-step reasoning. Built from PixMo-Count and PixMo-Points. Used to fine-tune vision-language models (e.g., Qwen2.5-VL) on visual counting with chain-of-thought reason