Can someone please publish an example in javascript (transformers.js) how to use this model to create video description?
#6
by
zlelik
- opened
I found an example for image here https://huggingface.co/onnx-community/Qwen2-VL-2B-Instruct, and it works nicely, but I cannot make it work for video :(
I put my code here https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct/discussions/27 maybe someone can help and point me what I am doing wrong?