p71924506
/
CPM-9G-8B
forked from p83651209/CPM-9G-8B
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
155 Commits 2 Branches 0 Tags 1.2 GiB
Python 98.2%
Shell 1.8%
Go to file
p83651209 cc5b9a5ad8 Update README.md 2024-11-02 17:00:02 +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 17:00:02 +08:00
inference.py ADD file via upload 2024-11-02 16:15:33 +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： https://www.alipan.com/s/FTPWUSBuz7s

docker: https://www.alipan.com/s/FTPWUSBuz7s

train_data: https://www.alipan.com/s/FTPWUSBuz7s