Chat with Video File using Qwen2 VL Model

[@tianyiluo2991]

thank you sir

[@shobhitsadwal6081]

hey man this was just awesome, can you recommend me what are the prerequisites that I need to study before this , should I take a deep learning course to understand this ? like can you please show me the path for it. subbed.

[@ESLRepeat]

absolutely amazing

[@AIAnytime]

Thanks

[@VIKASCHELLURU]

you are doing best bro

[@AIAnytime]

Thanks for the support

[@nadirzefra2374]

Why does it could'nt run on colab t4? The problem occur when install accelerate

[@IsmailIfakir]

multimodal llm can fine-tuning for sentiment analysis

[@АлексейСтребков-ж6и]

please make a video about Qwen2-Math

[@AIAnytime]

Soon

[@yusufersayyem7242]

Perfect😍

[@AIAnytime]

Thanks

[@suresht1885]

Brother: Can this go with any other Vision model. Or qwen family specific?

[@AIAnytime]

Qwen family mostly. For others, you would need to change the code a bit.

[@Rits1804-l4r]

brother can you finetune llama 3.1 8 b for Hindi translation task

[@yazanrisheh5127]

I am confused about 1 thing. Is it transcribing the video into text and then answers based on that or is it splitting the video into frames and its using the vision capabilities to understand image

[@NGGrandPlazaGhansoli-rr6yw]

its using vision to directly understand from image data .

[@QorQar]

Question does it work in colab t4?

[@QorQar]

I tried to run the code on the form page and it gives errors

[@QorQar]

Erorr with t4