Fine Tune Multimodal LLM "Idefics 2" using QLoRA

[@cklam123456789]

One day , I will visit you in India for a gathering ! Your work is amazing !!

[@AIAnytime]

Oh wow... I am waiting.

[@adityashinde436]

Thanks for this video, i was looking for this video. as you said most of them are just releasing LLM's and fine tuning it but few like LLAVA and idefics brought open source multimodal llms which is can fine tuned. i hope big players like mistral and llama bring their own multimodal llms very soon which are powerful as gpt4 vision and gemini vision

[@明明马-c6n]

yeah，me too

[@rajkachhadiya6192]

in the demo they define some parameters, here you are fine-tuning greedy models. if I want to fine-tune the model based on parameters, how can I do that?

[@ArtistrystoriesUnleashed45]

hi, how can i do inferencing on locally stored images?

[@mohsenghafari7652]

Hi dear friend .
Thank you for your efforts .
How to use this tutorial in PDFs at other language (for example Persian )
What will the subject ?
I made many efforts and tested different models, but the results in asking questions about pdfs are not good and accurate!
Thank you for the explanation

[@DialogoAi]

great video!
how does this cmapre with other multimodals like llava or qwen ?

[@AIAnytime]

Equally good...

[@ritikchaurasia708]

How to check which multmodel is good for our system

[@KleiAliaj-us9ip]

Hi bro,
i love your videos
I will try this today, but wanted to ask if i can i use colab t4 gpu to fine tune this ?

[@sneharoy3566]

thanks for your video

[@AIAnytime]

So nice of you

[@xyh6552]

does it support OLLEMA?

[@kumargaurav2170]

Llama 3 multumodal LMM will be releasing soon as Meta has already mentioned

[@明明马-c6n]

thank you ！！

[@AIAnytime]

Welcome!

[@user-jk9zr3sc5h]

Does it support fsdp training?