awwwwwwwww!I NEED VISION!

#2
by luoluo74751 - opened

awwwwwwwww!I NEED VISION!

Edge0 org

It’s a vision-language model, not just an LLM — it accepts both image and text input.

It’s a vision-language model, not just an LLM — it accepts both image and text input.

ok?!BUT why no mmproj model?OR This model dont need vision model?

thank U

it was a mistake, we will upload it later

Edge0 org

The mmproj model has been uploaded, sorry for the inconvenience.
image

The mmproj model has been uploaded, sorry for the inconvenience.
image

OKOK!VERY thank U for your work!

wanglamao changed discussion status to closed

Sign up or log in to comment