Hugging Face's logo

sanps
/
fVLM-135M

Image-Text-to-Text
PyTorch
Safetensors
English
foveated_vlm
vision-language
video-understanding
foveated-attention
multimodal
smollm2
dinov2
Model card Files
xet
Community
fVLM-135M / configs
6.04 kB
  • 1 contributor
 History: 1 commit
sanps's picture
sanps
Upload fVLM-135M: Foveated Vision-Language Model (Stage 3 DPO)
6d320d6 verified