Closed russellorv closed 2 days ago
70B GPTQ finetuning requires at least 48GB VRAM per GPU, you should use fsdp+qlora without GPTQ model
@hiyouga Thanks for the very quick reply!) That is, by increasing the number of video cards to 8 A10G 24 Gb, I still won't solve the problem?
Is there a way to create a qlora adapter for the model I'm using - TechxGenus/Meta-Llama-3-70B-Instruct-GPTQ?
70B GPTQ finetuning requires at least 48GB VRAM per GPU
@hiyouga Sorry for asking again (but I need to figure it out) 70B GPTQ finetuning requires at least 48GB of total VRAM (in this case I have 96 Gb of VRAM) or 48GB VRAM on 1 video card ?
48GB on 1 video card
Reminder
System Info
Configured as 4*A10G graphics cards (total 96 Gb)
llamafactory-cli train examples/train_qlora/llama3_lora_sft_gptq.yaml
Reproduction
OUTPUT
Expected behavior
What resources are needed to train 70B GPTQ models using which qlora?
Others
No response