Image-to-Text
sentence-transformers
Safetensors
Transformers
qwen2_vl
Qwen2-VL
text-generation-inference

Model Fine-Tuning

#2
by mrodriguesoliv - opened

What computer resources should I have to train this model in another language?

What computer resources should I have to train this model in another language?

With 768 batch pixels you should need around 150GB VRAM so 6x 3090/4090 with a batch size of 2

Hi Team, Hi @paulml

Would you please share any examples (docs/tutorial/etc.) for fine tuning this model (to a specific domain) ?

Thanks a lot.

Sign up or log in to comment