423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 04:32:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source 
Former-commit-id: 66b0fe4e964ad4d882935910f5e512666c54c2b2
This commit is contained in:
hiyouga 2024-04-02 22:17:48 +08:00
parent 86513f28dc
commit 3b16f97c6c
2 changed files with 8 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -327,8 +327,8 @@ To enable FlashAttention-2 on the Windows platform, you need to install the prec
#### Use local environment
```bash
CUDA_VISIBLE_DEVICES=0 python src/train_web.py
# or CUDA_VISIBLE_DEVICES=0 python -m llmtuner.webui.interface
export CUDA_VISIBLE_DEVICES=0 # `set CUDA_VISIBLE_DEVICES=0` for Windows
python src/train_web.py # or python -m llmtuner.webui.interface
```
#### Use Docker
@ -370,10 +370,8 @@ Use `python src/train_bash.py -h` to display arguments description.
```bash
CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \
--model_name_or_path path_to_model \
--adapter_name_or_path path_to_lora_adapter \
--template default \
--finetuning_type lora \
--model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
--template mistral \
--infer_backend vllm
```

10
README_zh.md
View File

@ -327,8 +327,8 @@ pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/downl
#### 使用本地环境
```bash
CUDA_VISIBLE_DEVICES=0 python src/train_web.py
# 或 CUDA_VISIBLE_DEVICES=0 python -m llmtuner.webui.interface
export CUDA_VISIBLE_DEVICES=0 # Windows 使用 `set CUDA_VISIBLE_DEVICES=0`
python src/train_web.py # 或 python -m llmtuner.webui.interface
```
#### 使用 Docker
@ -370,10 +370,8 @@ docker compose -f ./docker-compose.yml up -d
```bash
CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \
--model_name_or_path path_to_model \
--adapter_name_or_path path_to_lora_adapter \
--template default \
--finetuning_type lora \
--model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
--template mistral \
--infer_backend vllm
```