sanps
/

fVLM-1.7B

Image-Text-to-Text

vision-language

video-understanding

foveated-attention

Eval Results (legacy)

Model card Files Files and versions

fVLM-1.7B / model_code

57.9 kB

1 contributor

History: 1 commit

sanps's picture

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

78b1e06 verified 6 days ago

__init__.py

0 Bytes

Upload fVLM-1.7B: Foveated Vision-Language Model (Stage 3 DPO) 6 days ago
encoder.py

15.5 kB

Upload fVLM-1.7B: Foveated Vision-Language Model (Stage 3 DPO) 6 days ago
model.py

42.5 kB

Upload fVLM-1.7B: Foveated Vision-Language Model (Stage 3 DPO) 6 days ago