knoopx / mobile-vlm

Lightweight and fast vision model, does a decent job captioning photos.

Vision 3B

652 Pulls Updated 6 months ago

6 months ago

d614b616cc22 · 6.0GB

model
llama
·
2.70B
·
F16
params
{"stop":["Q:","A:"],"temperature":0}
template
Q: {{ .Prompt }} A:
projector
clip
·
320M
·
F16

Readme

Source: https://huggingface.co/Blombert/MobileVLM-3B-GGUF