p04798526
/
LLaMA-Factory-310P3
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update readme

This commit is contained in:
hiyouga 2024-04-02 22:17:48 +08:00
parent fc7f1cc365
commit 66b0fe4e96
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 #### Use local environment
```bash ```bash
CUDA_VISIBLE_DEVICES=0 python src/train_web.py export CUDA_VISIBLE_DEVICES=0 # `set CUDA_VISIBLE_DEVICES=0` for Windows
# or CUDA_VISIBLE_DEVICES=0 python -m llmtuner.webui.interface python src/train_web.py # or python -m llmtuner.webui.interface
``` ```
#### Use Docker #### Use Docker
@ -370,10 +370,8 @@ Use `python src/train_bash.py -h` to display arguments description.
```bash ```bash
CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \ CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \
--model_name_or_path path_to_model \ --model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
--adapter_name_or_path path_to_lora_adapter \ --template mistral \
--template default \
--finetuning_type lora \
--infer_backend vllm --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 #### 使用本地环境
```bash ```bash
CUDA_VISIBLE_DEVICES=0 python src/train_web.py export CUDA_VISIBLE_DEVICES=0 # Windows 使用 `set CUDA_VISIBLE_DEVICES=0`
# 或 CUDA_VISIBLE_DEVICES=0 python -m llmtuner.webui.interface python src/train_web.py # 或 python -m llmtuner.webui.interface
``` ```
#### 使用 Docker #### 使用 Docker
@ -370,10 +370,8 @@ docker compose -f ./docker-compose.yml up -d
```bash ```bash
CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \ CUDA_VISIBLE_DEVICES=0 API_PORT=8000 python src/api_demo.py \
--model_name_or_path path_to_model \ --model_name_or_path mistralai/Mistral-7B-Instruct-v0.2 \
--adapter_name_or_path path_to_lora_adapter \ --template mistral \
--template default \
--finetuning_type lora \
--infer_backend vllm --infer_backend vllm
``` ```