LLaMA-Factory双卡4090微调DeepSeek-R1-Distill-Qwen-14B医学领域

unsloth单卡4090微调DeepSeek-R1-Distill-Qwen-14B医学领域后，跑通一下多卡微调。

1，准备2卡RTX 4090

2，准备数据集

医学领域

pip install -U huggingface_hub
export HF_ENDPOINT=https://hf-mirror.com
huggingface-cli download --resume-download --repo-type dataset FreedomIntelligence/medical-o1-reasoning-SFT --local-dir FreedomIntelligence/medical-o1-reasoning-SFT 

3，安装LLaMA-Factory 和下载模型

需要提前搭建好docker微调环境

下载模型 ，需要是 safetensors 权重文件

git clone --depth 1 https://github.com/hiyouga/LLaMA-Factory.git

cd LLaMA-Factory

pip install -e ".[torch,metrics]"

llamafactory-cli webui

# llamafactory-cli version

INFO 04-12 04:48:24 __init__.py:190] Automatically detected platform cuda.

----------------------------------------------------------

| Welcome to LLaMA Factory, version 0.9.3.dev0 |

| |

| Project page: https://github.com/hiyouga/LLaMA-Factory |

----------------------------------------------------------

/workspace# python toShareGPT.py 转换数据集

4，注册数据集

cp /datasets/medical_sharegpt_format.json ./LLaMA-Factory/data/

修改 `data/dataset_info.json`，添加自定义数据集：

"medical_sharegpt_format": {

"file_name": "medical_sharegpt_format.json",

"formatting": "sharegpt",

"columns": {

"messages": "conversations",

"system": "system"

}

}

5，llamafactory-cli webui训练