安装环境
- pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
- pip install modelscope vllm 'ms-swift[llm]' -U
下载模型
- modelscope download --model Qwen/Qwen2.5-7B-Instruct --local_dir ./Qwen2.5-7B-Instruct
微调
-
实验环境：4 * A100# 显存占用：4 * 70GB
NPROC_PER_NODE=4 CUDA_VISIBLE_DEVICES=0,1,2,3 swift sft \ --model_type qwen2_5-72b-instruct \ --model_id_or_path Qwen2.5-72B-Instruct \ --dataset qwen2-pro-en#500 qwen2-pro-zh#500 self-cognition#500 \ --logging_steps 5 \ --learning_rate 1e-4 \ --output_dir output \ --lora_target_modules ALL \ --model_name 小黄 'Xiao Huang' \ --model_author 魔搭 ModelScope \ --deepspeed default-zero3 -
单卡A10/3090可运行的例子 （Qwen2.5-7B-Instruct）# 显存占用：24GB
CUDA_VISIBLE_DEVICES=0 swift sft \ --model_type qwen2_5-7b-instruct \ --model_id_or_path Qwen2.5-7B-Instruct \ --dataset qwen2-pro-en#500 qwen2-pro-zh#500 self-cognition#500 \ --logging_steps 5 \ --max_length 2048 \ --learning_rate 1e-4 \ --output_dir output \ --lora_target_modules ALL \ --model_name 小黄 'Xiao Huang' \ --model_author 魔搭 ModelScope
融合lora
CUDA_VISIBLE_DEVICES=0,1 swift export \
--ckpt_dir output/qwen2_5-72b-instruct/vx-xxx/checkpoint-xxx \
--merge_lora true
vLLM部署
vllm serve xxxxx-checkpoint-merged [opentional args]