appledora/DORI-Benchmark download history

appledora/DORI-Benchmark is an image text to text dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,112 times (22 in the last 7 days), and 11,463 times in total. It ranks #17,854 among datasets by monthly downloads.

Dataset Details Dataset Description DORI (Discriminative Orientation Reasoning Intelligence) is a comprehensive benchmark designed to evaluate object orientation understanding in multimodal large language models (MLLMs). The benchmark isolates and evaluates orientation

Models trained on DORI-Benchmark

1 models list it as training data.

• appledora/QWEN2.5-3B-Instruct-DORI-tuned 17 downloads in 30 days

Open appledora/DORI-Benchmark on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.