inclusionAI/ViLaSR download history
inclusionAI/ViLaSR is an 8.3B-parameter image text to text model by inclusionAI. In the last 30 days it was downloaded 181 times (52 in the last 7 days), and 30,162 times in total.
It ranks #144,101 on the Hub by monthly downloads and #7,351 among image text to text models.
It has 18 likes.
It is a fine-tune of Qwen/Qwen2.5-VL-7B-Instruct.
1 models build on ViLaSR: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 972 times in the last 30 days. See the ViLaSR galaxy.
Most downloaded derivatives
- mradermacher/ViLaSR-GGUF (quantized), 791 downloads in 30 days