deepgeek/MiniCPM-o
2
0
Fork 0
mirror of https://github.com/OpenBMB/MiniCPM-V.git synced 2026-02-04 09:49:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #71 from HwwwwwwwH/main

Browse Source 
Add description of vLLM support in README&README_en
This commit is contained in:
Hongji Zhu
2024-04-24 13:35:46 +08:00
committed by GitHub
parent 5c6cb64a3c 868a5afaeb
commit e901ec96b3
2 changed files with 53 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
README.md
View File

@@ -27,6 +27,7 @@
## 更新日志 <!-- omit in toc -->
* [2024.04.23] 我们增加了对 [vllm](#vllm) 的支持，欢迎体验！
* [2024.04.18] 我们在 HuggingFace Space 新增了 MiniCPM-V 2.0 的 [demo](https://huggingface.co/spaces/openbmb/MiniCPM-V-2)，欢迎体验！
* [2024.04.17] MiniCPM-V 2.0 现在支持用户部署本地 [WebUI Demo](#本地webui-demo部署) 了，欢迎试用!
* [2024.04.15] MiniCPM-V 2.0 现在可以通过 SWIFT 框架 [微调](https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/minicpm-v-2最佳实践.md) 了，支持流式输出!
@@ -628,6 +629,33 @@ PYTORCH_ENABLE_MPS_FALLBACK=1 python web_demo.py --device mps --dtype fp16
```
</details>
### vLLM 部署 <a id='vllm'></a>
<details>
<summary>点击查看 vLLM 部署运行的方法</summary>
由于我们对 vLLM 提交的 PR 还在 review 中，因此目前我们 fork 了一个 vLLM 仓库以供测试使用。
1. 首先克隆我们 fork 的 vLLM 库:
```shell
git clone https://github.com/OpenBMB/vllm.git
```
2. 安装 vLLM 库:
```shell
cd vllm
pip install -e .
```
3. 安装 timm 库:
```shell
pip install timm=0.9.10
```
4. 测试运行示例程序:
```shell
python examples/minicpmv_example.py
```
</details>
## 微调
### MiniCPM-V <!-- omit in toc -->

25
README_en.md
View File

@@ -25,6 +25,7 @@
## News <!-- omit in toc -->
* [2024.04.23] MiniCPM-V-2.0 supports vLLM now! Click [here](#vllm) to view more details.
* [2024.04.18] We create a HuggingFace Space to host the demo of MiniCPM-V 2.0 at [here](https://huggingface.co/spaces/openbmb/MiniCPM-V-2)!
* [2024.04.17] MiniCPM-V-2.0 supports deploying [WebUI Demo](#webui-demo) now!
* [2024.04.15] MiniCPM-V-2.0 now also supports [fine-tuning](https://github.com/modelscope/swift/blob/main/docs/source/Multi-Modal/minicpm-v-2最佳实践.md) with the SWIFT framework!
@@ -620,6 +621,30 @@ PYTORCH_ENABLE_MPS_FALLBACK=1 python web_demo.py --device mps --dtype fp16
```
</details>
### Inference with vLLM<a id="vllm"></a>
<details>
<summary>Click to see how to inference with vLLM </summary>
Because our pull request to vLLM is still waiting for reviewing, we fork this repository to build and test our vLLM demo. Here are the steps:
1. Clone our version of vLLM:
```shell
git clone https://github.com/OpenBMB/vllm.git
```
2. Install vLLM:
```shell
cd vllm
pip install -e .
```
3. Install timm:
```shell
pip install timm=0.9.10
```
4. Run our demo:
```shell
python examples/minicpmv_example.py
```
</details>
## Finetune