"vscode:/vscode.git/clone" did not exist on "563d441b000ad95c90f70ad77018c410a4626637"
Commit a1ace045 authored by chenzk's avatar chenzk
Browse files

Update sc.md

parent 6ca99460
......@@ -65,6 +65,8 @@ pip install -e ".[torch,metrics]" # 安装llamafactory-cli=0.9.1
```
## 数据集
数据集快速下载中心:[SCNet AIDatasets](https://www.scnet.cn/ui/aihub/datasets)
[identity](https://huggingface.co/datasets/mrfakename/identity)`alpaca_en_demo`根据源github说明文档进行获取
项目中已提供用于试验训练的迷你数据集:[`identity`](./data/identity.json)[`alpaca_en_demo`](./data/alpaca_en_demo.json),训练数据目录结构如下:
......@@ -150,6 +152,8 @@ DCU与GPU精度一致,推理框架:pytorch。
`制造,广媒,金融,能源,医疗,家居,教育`
## 预训练权重
Hugging Face下载地址为:[Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
预训练权重快速下载中心:[SCNet AIModels](https://www.scnet.cn/ui/aihub/models) ,项目中的预训练权重可从快速下载通道下载:[Llama-3.2-3B-Instruct](https://www.scnet.cn/ui/aihub/models/icszy_zs_ai/Llama-3.2-3B-Instruct)
## 源码仓库及问题反馈
- http://developer.sourcefind.cn/codes/modelzoo/llama-factory-llama3.2_pytorch.git
## 参考资料
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment