llama.cpp icon indicating copy to clipboard operation
llama.cpp copied to clipboard
Published 3 months ago • verified publisher icon ggml-org

Feature Request: Support for Florence-2 Vision Models

Open criminact opened this issue 1 year ago • 2 comments

Feature Description

Support for Florence-2 Family of Vision Models needed

Motivation

A 400M model beating a 15-16B parameter model in benchmarks?

Possible Implementation

No response

criminact avatar Jun 19 '24 13:06 criminact

Links for anyone interested.

Models:

  • https://huggingface.co/microsoft/Florence-2-base/
  • https://huggingface.co/microsoft/Florence-2-large/
  • https://huggingface.co/microsoft/Florence-2-base-ft/
  • https://huggingface.co/microsoft/Florence-2-large-ft/

Demo:

  • https://huggingface.co/spaces/SixOpen/Florence-2-large-ft

theolivenbaum avatar Jun 20 '24 09:06 theolivenbaum

Is anyone working on this?

lijianxing123 avatar Jul 22 '24 02:07 lijianxing123

This issue was closed because it has been inactive for 14 days since being marked as stale.

github-actions[bot] avatar Sep 08 '24 01:09 github-actions[bot]

I don't think this is stale, bot.

swittk avatar Sep 11 '24 09:09 swittk