Hugging Face's logo

sanps
/
fVLM-1.7B

Image-Text-to-Text
PyTorch
Safetensors
English
foveated_vlm
vision-language
video-understanding
foveated-attention
multimodal
smollm2
dinov2
Eval Results (legacy)
Model card Files
xet
Community
fVLM-1.7B / model_code /model.py

Commit History

Upload fVLM-1.7B: Foveated Vision-Language Model (Stage 3 DPO)
78b1e06
verified

sanps commited on