microsoft/Phi-3.5-vision-instruct download history
microsoft/Phi-3.5-vision-instruct is a 4.1B-parameter image text to text model by microsoft. In the last 30 days it was downloaded 825,690 times (219,484 in the last 7 days), and 20,511,358 times in total.
It ranks #477 on the Hub by monthly downloads and #77 among image text to text models.
It has 739 likes.
34 models build on Phi-3.5-vision-instruct: 13 quantized, 18 fine-tuned, 3 adapters and 0 merges. Together with the original they were downloaded 1,012,109 times in the last 30 days. See the Phi-3.5-vision-instruct galaxy.
Most downloaded derivatives
- TIGER-Lab/VLM2Vec-Full (finetune), 182.5K downloads in 30 days
- OpenVINO/Phi-3.5-vision-instruct-int8-ov (quantized), 878 downloads in 30 days
- TIGER-Lab/VLM2Vec-LoRA (finetune), 476 downloads in 30 days
- OpenVINO/Phi-3.5-vision-instruct-int4-ov (quantized), 461 downloads in 30 days
- mlc-ai/Phi-3.5-vision-instruct-q4f16_1-MLC (quantized), 320 downloads in 30 days
- microsoft/Phi-Ground-Any (finetune), 292 downloads in 30 days
- microsoft/Phi-Ground (finetune), 248 downloads in 30 days
- DeepGlint-AI/UniME-Phi3.5-V-4.2B (finetune), 237 downloads in 30 days
- nm-testing/Phi-3.5-vision-instruct-FP8-dynamic (quantized), 188 downloads in 30 days
- yifeihu/TB-OCR-preview-0.1 (finetune), 134 downloads in 30 days
- OpenVINO/Phi-3.5-vision-instruct-fp16-ov (finetune), 133 downloads in 30 days
- onnx-community/Phi-3.5-vision-instruct (quantized), 133 downloads in 30 days