Commit 5f1e23b8 authored by Rayyyyy's avatar Rayyyyy
Browse files

Update README

parent e91dbf8f
Pipeline #2646 failed with stages
in 0 seconds
......@@ -29,7 +29,7 @@ GLM-Z1-Rumination-32B-0414 是具有沉思能力的深度推理模型(对标 O
dcoker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.4.1-ubuntu22.04-dtk25.04-py3.10
docker run -it --shm-size 200g --network=host --name {docker_name} --privileged --device=/dev/kfd --device=/dev/dri --device=/dev/mkfd --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro {imageID} bash
cd /your_code_path/glm-4-z1_pytorch
cd /your_code_path/glm-z1_pytorch
pip install transformers>=4.51.3
```
......@@ -39,7 +39,7 @@ cd docker
docker build --no-cache -t glm4-z1:latest .
docker run -it --shm-size 200g --network=host --name {docker_name} --privileged --device=/dev/kfd --device=/dev/dri --device=/dev/mkfd --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -u root -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro {imageID} bash
cd /your_code_path/glm-4-z1_pytorch
cd /your_code_path/glm-z1_pytorch
pip install transformers>=4.51.3
```
......@@ -64,7 +64,7 @@ pip install transformers>=4.51.3
## 训练
### Llama Factory 微调方法(推荐)
1. 训练库安装(**非glm-4-z1_pytorch目录下**),安装版本**大于 v0.9.2**`Llama-Factory`具体安装方法请参考仓库的README。
1. 训练库安装(**非glm-z1_pytorch目录下**),安装版本**大于 v0.9.2**`Llama-Factory`具体安装方法请参考仓库的README。
```
git clone https://developer.sourcefind.cn/codes/OpenDAS/llama-factory
```
......@@ -117,7 +117,7 @@ python infer_transformers.py --model_path THUDM/GLM-Z1-9B-0414
- [GLM-Z1-32B-0414](https://huggingface.co/THUDM/GLM-Z1-32B-0414)
## 源码仓库及问题反馈
- https://developer.sourcefind.cn/codes/modelzoo/glm-4-z1_pytorch
- https://developer.sourcefind.cn/codes/modelzoo/glm-z1_pytorch
## 参考资料
- https://github.com/THUDM/GLM-4
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