8000 test link valid by Jintao-Huang · Pull Request #4265 · modelscope/ms-swift · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

test link valid #4265

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
May 18, 2025
Merged

test link valid #4265

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
ed845d2
update
Jintao-Huang May 18, 2025
72c224d
update
Jintao-Huang May 18, 2025
3b4dc17
update
Jintao-Huang May 18, 2025
0e6b89d
update
Jintao-Huang May 18, 2025
f56c14d
update
Jintao-Huang May 18, 2025
ab53098
update
Jintao-Huang May 18, 2025
7e01bec
update
Jintao-Huang May 18, 2025
824a9f1
update
Jintao-Huang May 18, 2025
4bbb14a
update
Jintao-Huang May 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion CONTRIBUTING.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ Please refer to our [Code of Conduct documentation](./CODE_OF_CONDUCT.md).
### Submitting PR (Pull Requests)

Any feature development is carried out in the form of Fork and then PR on GitHub.
1. Fork: Go to the [SWIFT](https://github.com/modelscope/swift) page and click the **Fork button**. After completion, a SWIFT code repository will be cloned under your personal organization.
1. Fork: Go to the [ms-swift](https://github.com/modelscope/ms-swift) page and click the **Fork button**. After completion, a SWIFT code repository will be cloned under your personal organization.
2. Clone: Clone the code repository generated in the first step to your local machine and **create a new branch** for development. During development, please click the **Sync Fork button** in time to synchronize with the `main` branch to prevent code expiration and conflicts.
3. Submit PR: After development and testing, push the code to the remote branch. On GitHub, go to the **Pull Requests page**, create a new PR, select your code branch as the source branch, and the `modelscope/swift:main` branch as the target branch.

Expand Down
2 changes: 1 addition & 1 deletion CONTRIBUTING_CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@

10000 任何feature开发都在github上以先Fork后PR的形式进行。

1. Fork：进入[SWIFT](https://github.com/modelscope/swift)页面后，点击**Fork按钮**执行。完成后会在您的个人组织下克隆出一个SWIFT代码库
1. Fork：进入[ms-swift](https://github.com/modelscope/ms-swift)页面后，点击**Fork按钮**执行。完成后会在您的个人组织下克隆出一个SWIFT代码库

2. Clone：将第一步产生的代码库clone到本地并**拉新分支**进行开发，开发中请及时点击**Sync Fork按钮**同步`main`分支，防止代码过期并冲突

Expand Down
10 changes: 5 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,9 +16,9 @@
<img src="https://img.shields.io/badge/pytorch-%E2%89%A52.0-orange.svg">
<a href="https://github.com/modelscope/modelscope/"><img src="https://img.shields.io/badge/modelscope-%E2%89%A51.19-5D91D4.svg"></a>
<a href="https://pypi.org/project/ms-swift/"><img src="https://badge.fury.io/py/ms-swift.svg"></a>
<a href="https://github.com/modelscope/swift/blob/main/LICENSE"><img src="https://img.shields.io/github/license/modelscope/swift"></a>
<a href="https://github.com/modelscope/ms-swift/blob/main/LICENSE"><img src="https://img.shields.io/github/license/modelscope/ms-swift"></a>
<a href="https://pepy.tech/project/ms-swift"><img src="https://pepy.tech/badge/ms-swift"></a>
<a href="https://github.com/modelscope/swift/pulls"><img src="https://img.shields.io/badge/PR-welcome-55EB99.svg"></a>
<a href="https://github.com/modelscope/ms-swift/pulls"><img src="https://img.shields.io/badge/PR-welcome-55EB99.svg"></a>
</p>

<p align="center">
Expand Down Expand Up @@ -279,10 +279,10 @@ Supported Training Methods:
|------------------------------------|--------------------------------------------------------------|---------------------------------------------------------------------------------------------|--------------------------------------------------------------|--------------------------------------------------------------|--------------------------------------------------------------|----------------------------------------------------------------------------------------------|
| Pre-training | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/pretrain/train.sh) | ✅ | ✅ | ✅ | ✅ | ✅ |
| Instruction Supervised Fine-tuning | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/full/train.sh) | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/lora_sft.sh) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/qlora) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/multi-gpu/deepspeed) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/multi-node) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/multimodal) |
| DPO Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/multimodal/rlhf/dpo.sh) |
| GRPO Training | [✅]((https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/internal/grpo_zero2.sh)) | ✅ | ✅ | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/internal/multi_node) | ✅ |
| DPO Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/multimodal/rlhf/dpo) |
| GRPO Training | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/internal) | ✅ | ✅ | ✅ | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/grpo/external) | ✅ |
| Reward Model Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/rm.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/rm.sh) | ✅ | ✅ |
| PPO Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo.sh) | ✅ | ❌ |
| PPO Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo) | ✅ | ❌ |
| KTO Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/kto.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/kto.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/multimodal/rlhf/kto.sh) |
| CPO Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/cpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/cpo.sh) | ✅ | ✅ |
| SimPO Training | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/simpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/simpo.sh) | ✅ | ✅ |
Expand Down
10 changes: 5 additions & 5 deletions README_CN.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,9 @@
<img src="https://img.shields.io/badge/pytorch-%E2%89%A52.0-orange.svg">
<a href="https://github.com/modelscope/modelscope/"><img src="https://img.shields.io/badge/modelscope-%E2%89%A51.19-5D91D4.svg"></a>
<a href="https://pypi.org/project/ms-swift/"><img src="https://badge.fury.io/py/ms-swift.svg"></a>
<a href="https://github.com/modelscope/swift/blob/main/LICENSE"><img src="https://img.shields.io/github/license/modelscope/swift"></a>
<a href="https://github.com/modelscope/ms-swift/blob/main/LICENSE"><img src="https://img.shields.io/github/license/modelscope/ms-swift"></a>
<a href="https://pepy.tech/project/ms-swift"><img src="https://pepy.tech/badge/ms-swift"></a>
<a href="https://github.com/modelscope/swift/pulls"><img src="https://img.shields.io/badge/PR-welcome-55EB99.svg"></a>
<a href="https://github.com/modelscope/ms-swift/pulls"><img src="https://img.shields.io/badge/PR-welcome-55EB99.svg"></a>
</p>

<p align="center">
Expand Down Expand Up @@ -268,10 +268,10 @@ print(f'response: {resp_list[0].choices[0].message.content}')
| ------ | ------ |---------------------------------------------------------------------------------------------| ----- | ------ | ------ |----------------------------------------------------------------------------------------------|
| 预训练 | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/pretrain/train.sh) | ✅ | ✅ | ✅ | ✅ | ✅ |
| 指令监督微调 | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/full/train.sh) | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/lora_sft.sh) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/qlora) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/multi-gpu/deepspeed) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/multi-node) | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/multimodal) |
| DPO训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/multimodal/rlhf/dpo.sh) |
| GRPO训练 | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/internal/grpo_zero2.sh) | ✅ | ✅ | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/internal/multi_node) | ✅ |
| DPO训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/dpo) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/multimodal/rlhf/dpo) |
| GRPO训练 | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/grpo/internal) | ✅ | ✅ | ✅ | [✅](https://github.com/modelscope/ms-swift/tree/main/examples/train/grpo/external) | ✅ |
| 奖励模型训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/rm.sh) | AE88 | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/rm.sh) | ✅ | ✅ |
| PPO训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo.sh) | ✅ | ❌ |
| PPO训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/ppo) | ✅ | ❌ |
| KTO训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/kto.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/kto.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/multimodal/rlhf/kto.sh) |
| CPO训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/cpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/cpo.sh) | ✅ | ✅ |
| SimPO训练 | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/simpo.sh) | ✅ | [✅](https://github.com/modelscope/ms-swift/blob/main/examples/train/rlhf/simpo.sh) | ✅ | ✅ |
Expand Down
1 change: 0 additions & 1 deletion docs/source/BestPractices/NPU支持.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
# NPU支持
作者: [chuanzhubin](https://github.com/chuanzhubin)

## 环境准备

Expand Down
18 changes: 9 additions & 9 deletions docs/source/Customization/插件化.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

## callback回调

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/callback.py).
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/callback.py).

`callback`机制是transformers Trainer中的一种训练定制化机制。开发者可以在callback中控制训练流程。通常来说，callback的定制化类似下面的样子：
```python
Expand All @@ -27,7 +27,7 @@ extra_callbacks = [CustomCallback()]

## 定制化loss

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/loss.py).
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/loss.py).

SWIFT支持在plugin中定制loss。如果不使用这个能力，默认会使用交叉熵Loss（CE Loss）。开发者可以在这个文件中编写代码，注册后trainer会自动使用你定制的loss方法。
例如在plugin/loss.py中添加下面的代码：
Expand All @@ -41,7 +41,7 @@ def loss_scale_func(outputs, labels, loss_scale=None, num_items_in_batch=None) -

## 定制化loss_scale

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/loss_scale/loss_scale.py).
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/loss_scale/loss_scale.py).

loss_scale机制在SWIFT中是非常重要的机制之一。在pt和sft任务中，可训练token的loss是均匀的，即每个token平等的进行bp。但在某些情况下，某些token的权重比较大，需要被额外关注，
在这种情况下就需要更高的权重。loss_scale可以让开发者自由地定义自己的token权重。
Expand All @@ -65,7 +65,7 @@ class LastRoundLossScale(LossScale):

## 定制化metric

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/metric.py).
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/metric.py).

metric可以定制训练时使用的评测参数：
```python
Expand All @@ -83,7 +83,7 @@ def get_metric(metric: str):

## 定制化optimizer

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/optimizer.py).
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/optimizer.py).
- 对模型不同部分采用不同的学习率，例如：ViT和LLM分别使用不同的学习率，参考[这里](https://github.com/modelscope/ms-swift/blob/main/examples/train/multimodal/lora_llm_full_vit/custom_plugin.py)。

用户可以在这里增加自己的optimizer和lr_scheduler实现：
Expand All @@ -106,11 +106,11 @@ optimizers_map = {

## 定制化agent template

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/agent_template).
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/agent_template).

## 定制化tuner

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/tuner.py).
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/tuner.py).
- 多模态模型对ViT部分使用全参数训练，LLM部分使用LoRA训练，参考[这里](https://github.com/modelscope/ms-swift/tree/main/examples/train/multimodal/lora_llm_full_vit)。
- Phi4-multimodal，直接对其已有LoRA进行训练而不额外附加LoRA，参考[这里](https://github.com/modelscope/ms-swift/blob/main/examples/train/plugins/tuner_phi4_mm.sh)。

Expand Down Expand Up @@ -150,7 +150,7 @@ class IA3(Tuner):

## PRM

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/prm.py)。
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/prm.py)。

PRM是过程奖励模型，PRM会在`swift sample`命令中使用。PRM需要支持的接口比较简单：
```python
Expand Down Expand Up @@ -178,7 +178,7 @@ So, the answer is ...

## ORM

example在[这里](https://github.com/modelscope/swift/blob/main/swift/plugin/orm.py)。
example在[这里](https://github.com/modelscope/ms-swift/blob/main/swift/plugin/orm.py)。

ORM是结果奖励模型。ORM一般使用正则表达式来进行，ORM决定了response是否是正确的。例如 4D14 ：

Expand Down
Loading
0