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 2024-05-28 19:35:52 +08:00
parent 7c016b22aa
commit 087b9faa39
3 changed files with 6 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
README.md
View File

@ -395,9 +395,6 @@ See [examples/README.md](examples/README.md) for advanced usage (including distr
### Fine-Tuning with LLaMA Board GUI (powered by [Gradio](https://github.com/gradio-app/gradio)) ### Fine-Tuning with LLaMA Board GUI (powered by [Gradio](https://github.com/gradio-app/gradio))
> [!IMPORTANT]
> LLaMA Board GUI only supports training on a single GPU.
#### Use local environment #### Use local environment
```bash ```bash
@ -451,7 +448,7 @@ export USE_MODELSCOPE_HUB=1 # `set USE_MODELSCOPE_HUB=1` for Windows
Train the model by specifying a model ID of the ModelScope Hub as the `model_name_or_path`. You can find a full list of model IDs at [ModelScope Hub](https://modelscope.cn/models), e.g., `LLM-Research/Meta-Llama-3-8B-Instruct`. Train the model by specifying a model ID of the ModelScope Hub as the `model_name_or_path`. You can find a full list of model IDs at [ModelScope Hub](https://modelscope.cn/models), e.g., `LLM-Research/Meta-Llama-3-8B-Instruct`.
### Use W&B Logging ### Use W&B Logger
To use [Weights & Biases](https://wandb.ai) for logging experimental results, you need to add the following arguments. To use [Weights & Biases](https://wandb.ai) for logging experimental results, you need to add the following arguments.
@ -460,6 +457,8 @@ report_to: wandb
run_name: test_run # optional run_name: test_run # optional
``` ```
Set `WANDB_API_KEY` to [your key](https://wandb.ai/authorize) when launching training tasks to log in with your W&B account.
## Projects using LLaMA Factory ## Projects using LLaMA Factory
If you have a project that should be incorporated, please contact via email or create a pull request. If you have a project that should be incorporated, please contact via email or create a pull request.

5
README_zh.md
View File

@ -395,9 +395,6 @@ CUDA_VISIBLE_DEVICES=0 llamafactory-cli export examples/merge_lora/llama3_lora_s
### LLaMA Board 可视化微调（由 [Gradio](https://github.com/gradio-app/gradio) 驱动） ### LLaMA Board 可视化微调（由 [Gradio](https://github.com/gradio-app/gradio) 驱动）
> [!IMPORTANT]
> LLaMA Board 可视化界面目前仅支持单 GPU 训练。
#### 使用本地环境 #### 使用本地环境
```bash ```bash
@ -458,6 +455,8 @@ report_to: wandb
run_name: test_run # 可选 run_name: test_run # 可选
``` ```
在启动训练任务时，将 `WANDB_API_KEY` 设置为[密钥](https://wandb.ai/authorize)来登录 W&B 账户。
## 使用了 LLaMA Factory 的项目 ## 使用了 LLaMA Factory 的项目
如果您有项目希望添加至下述列表，请通过邮件联系或者创建一个 PR。 如果您有项目希望添加至下述列表，请通过邮件联系或者创建一个 PR。

3
src/llamafactory/cli.py
View File

@ -4,8 +4,7 @@ import subprocess
import sys import sys
from enum import Enum, unique from enum import Enum, unique
from llamafactory import launcher from . import launcher
from .api.app import run_api from .api.app import run_api
from .chat.chat_model import run_chat from .chat.chat_model import run_chat
from .eval.evaluator import run_eval from .eval.evaluator import run_eval