Go to file
p83651209 124160cb1e Add model_final 2024-11-03 12:49:21 +08:00
FM_9G fix single dataset error with exhaust with 2b models 2024-08-01 10:37:57 +08:00
quick_start_clean Update README.md 2024-09-14 16:15:16 +08:00
LLaMA-Factory.zip ADD file via upload 2024-11-02 16:52:22 +08:00
README.md Update README.md 2024-11-02 17:48:43 +08:00
inference.py ADD file via upload 2024-11-02 16:15:33 +08:00
model_final Add model_final 2024-11-03 12:49:21 +08:00
test_case.json ADD file via upload 2024-11-02 16:18:55 +08:00
train.sh ADD file via upload 2024-11-02 16:32:04 +08:00

README.md

方案: 全参数微调,使用不同数据集训练多个模型和推理时增强进行融合。

训练代码: LLaMA-Factory.zip 解压后使用,可参照https://github.com/hiyouga/LLaMA-Factory配置环境或将代码映射到docker中使用。 训练train.sh。将数据集放到LLaMA-Factory/data文件夹下将train.sh放到LLaMA-Factory下使用。 推理: python inference.py(需在inference.py中修改好模型路径。) test_case.json是从题目中提取出来的测试用例。

百度网盘需要收费,使用阿里云盘 model_wight:通过百度网盘分享的文件: 链接:https://pan.baidu.com/s/1paYNO7d5OYESuyw3BVo7Ew 提取码6666 https://www.alipan.com/s/FTPWUSBuz7s

docker: 链接:https://pan.baidu.com/s/1paYNO7d5OYESuyw3BVo7Ew 提取码6666 https://www.alipan.com/s/FTPWUSBuz7s

train_data: 链接:https://pan.baidu.com/s/1paYNO7d5OYESuyw3BVo7Ew 提取码6666 https://www.alipan.com/s/FTPWUSBuz7s