LLaMA-Factory
LLaMA-Factory copied to clipboard
dpo单机多卡
Reminder
- [X] I have read the README and searched the existing issues.
Reproduction
dpo单机多卡,是不是可以直接使用,examples/lora_multi_gpu/single_node.sh,看脚本里写的, #!/bin/bash
CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch
--config_file examples/accelerate/single_config.yaml
src/train.py examples/lora_multi_gpu/llama3_lora_sft.yaml
是不是只需要换成llama3_lora_dpo.yaml 就可以使用了?
Expected behavior
No response
System Info
No response
Others
No response