mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-10-16 00:28:10 +08:00
update readme
Former-commit-id: 3a8c17907c71f46b1b37501e2afdc99ad89fb4bc
This commit is contained in:
parent
348f29aa50
commit
719585a128
14
README.md
14
README.md
@ -342,6 +342,16 @@ export GRADIO_SERVER_PORT=7860 # `set GRADIO_SERVER_PORT=7860` for Windows
|
||||
python src/train_web.py # or python -m llmtuner.webui.interface
|
||||
```
|
||||
|
||||
<details><summary>For Aliyun users</summary>
|
||||
|
||||
If you encountered display problems in LLaMA Board GUI, try using the following command to set environment variables before starting LLaMA Board:
|
||||
|
||||
```bash
|
||||
export GRADIO_ROOT_PATH=/${JUPYTER_NAME}/proxy/7860/
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
#### Use Docker
|
||||
|
||||
```bash
|
||||
@ -381,8 +391,8 @@ Use `python src/train_bash.py -h` to display arguments description.
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=0,1 API_PORT=8000 python src/api_demo.py \
|
||||
--model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
|
||||
--template mistral \
|
||||
--model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct \
|
||||
--template llama3 \
|
||||
--infer_backend vllm \
|
||||
--vllm_enforce_eager
|
||||
```
|
||||
|
14
README_zh.md
14
README_zh.md
@ -342,6 +342,16 @@ export GRADIO_SERVER_PORT=7860 # Windows 使用 `set GRADIO_SERVER_PORT=7860`
|
||||
python src/train_web.py # 或 python -m llmtuner.webui.interface
|
||||
```
|
||||
|
||||
<details><summary>阿里云用户指南</summary>
|
||||
|
||||
如果您在 LLaMA Board GUI 中遇到显示问题,请尝试在启动前使用以下命令设置环境变量:
|
||||
|
||||
```bash
|
||||
export GRADIO_ROOT_PATH=/${JUPYTER_NAME}/proxy/7860/
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
#### 使用 Docker
|
||||
|
||||
```bash
|
||||
@ -381,8 +391,8 @@ docker compose -f ./docker-compose.yml up -d
|
||||
|
||||
```bash
|
||||
CUDA_VISIBLE_DEVICES=0,1 API_PORT=8000 python src/api_demo.py \
|
||||
--model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
|
||||
--template mistral \
|
||||
--model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct \
|
||||
--template llama3 \
|
||||
--infer_backend vllm \
|
||||
--vllm_enforce_eager
|
||||
```
|
||||
|
Loading…
x
Reference in New Issue
Block a user