zzliang/GRIT download history
zzliang/GRIT is a text to image dataset on the Hugging Face Hub. In the last 30 days it was downloaded 760 times (127 in the last 7 days), and 20,261 times in total. It ranks #23,864 among datasets by monthly downloads.
GRIT: Large-Scale Training Corpus of Grounded Image-Text Pairs Dataset Summary We introduce GRIT, a large-scale dataset of Grounded Image-Text pairs, which is created based on image-text pairs from COYO-700M and LAION-2B. We construct a pipeline to extract and link text spans (
Models trained on GRIT
13 models list it as training data.
- segmind/SSD-1B 15.6K downloads in 30 days
- segmind/Segmind-Vega 2.6K downloads in 30 days
- nnethercott/llava-v1.5-7b-gpt4OCR-hf-GGUF_Q4_K_M 194 downloads in 30 days
- nnethercott/llava-v1.5-7b-gpt4OCR-hf-GGUF_Q2_K 120 downloads in 30 days
- kp-forks/SSD-1B 108 downloads in 30 days
- remiai3/ssd-1b 57 downloads in 30 days
- PrunaAI/Segmind-Vega-smashed 46 downloads in 30 days
- thingthatis/SSD-1B 44 downloads in 30 days
- ckpt/SSD-1B 24 downloads in 30 days
- Yung-shun/SSD-1B-openvino 23 downloads in 30 days
- nnethercott/llava-v1.5-7b-gpt4OCR-hf 22 downloads in 30 days
- nnethercott/llava-v1.5-7b-gpt4OCR-hf-AWQ 6 downloads in 30 days
Open zzliang/GRIT on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.