Fine Tune Qwen2 VL Model using Llama Factory

preview_player
Показать описание
In this video, I walk you through the step-by-step process of fine-tuning the Qwen2-VL model using LlamaFactory. You'll learn how to harness the power of Qwen2-VL, a state-of-the-art multimodal model, and LlamaFactory’s efficient framework for fine-tuning. From setting up your environment to optimizing the model for visual and video data processing, I cover everything you need to know to get started.

If you find this tutorial helpful, don’t forget to like, comment, and subscribe for more AI-related content!

Join this channel to get access to perks:

To further support the channel, you can contribute via the following methods:

Bitcoin Address: 32zhmo5T9jvu8gJDGW3LTuKBM1KPMHoCsW

#qwen2vl #ai #llm
Рекомендации по теме
Комментарии
Автор

Helped me in my fine tuning on image dataset

user-jw
Автор

How can we change it rank(r) and alpha value?

MayurKuchhadiya-fb
Автор

multimodal llm can fine-tuning for sentiment analysis

IsmailIfakir
Автор

Hi, pls let us know how to use the custom dataset from local folder or dataset from huggingface, which parameter we should change.

satheeshthangaraj
Автор

How to use different datasets and inferencing???

datadesigner
Автор

can you change your camera settings to mirror your video so that we can see the text correctly in the background (manchester united and other drawings on the board)

explorer
Автор

If I have created a chatbot with the 7b model will that model have a memory capacity like will it remember previous conversations?

arjunreddy
Автор

LlaMA-Factory is buggy. You can NOT finetune with vision tower open.

nguyenanhnguyen
Автор

suppose if have created a bot with these model will I can chat text to text ? and if give image as input and gave prompt and started chatting with bot and will it remember the previous history?

arjunreddy
Автор

Hey, thanks for. the video, you quite a smart guy, my question is about the Vision features of Qwen2 VL, can i wire my camera to make it able to my model to see?

cyberthugFi
Автор

Awesome video. I am the first one to comment. 🎉🎉

azizahtas
Автор

i like you videos but the flag behind you uhhh

NatnaelTamirat-bp
Автор

Can you please let me know how I could do inference, I had done training with the radio ui, have model saved in

satvik