FORCE_TORCHRUN=1 CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 llamafactory-cli train configs/qwen2_vl_full_sft.yaml
CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat configs/qwen2_vl_infer.yaml
Qwen2-VL在文旅领域的LLaMA-Factory微调案例 The case for fine-tuning Qwen2-VL in the field of historical literature and museums
FORCE_TORCHRUN=1 CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 llamafactory-cli train configs/qwen2_vl_full_sft.yaml
CUDA_VISIBLE_DEVICES=0 llamafactory-cli webchat configs/qwen2_vl_infer.yaml