I want to know the use of the gpu of MiniCPM-Llama3-V 2.5

[praymich]

I'd like to ask how much gpu memory is needed for this model inference and training

[iceflame89]

Inference with MiniCPM-Llama3-V 2.5 fp16 need at least 16 GB gpu memory, int4 need 8 GB gpu memory. Full parameter training need 8*A100 80GB, we will release lora fine-tuning code in several days, please stay tuned.

[Cuiunbo]

Add this to README

[praymich]

thank you very much