Xnhyacinth
/

Resadapt

Video-Text-to-Text

image-text-to-text

video-question-answering

text-generation-inference

Model card Files Files and versions

Resadapt / README.md

Xnhyacinth's picture

Update model card metadata

2d8daf5 verified 15 days ago

|

History Blame Contribute Delete

350 Bytes

library_name: transformers
pipeline_tag: video-text-to-text
tags:
  - qwen2.5-vl
  - video-question-answering
  - resadapt

Resadapt

This repository contains the Resadapt checkpoint.

Repository root: Qwen2.5-VL checkpoint.
pred/: trained SmolVLM predictor checkpoint.
predictor_smolv3_init/: initialization weights for the predictor.