update readme

Author: mingcomplex

README.md

@@ -17,6 +17,15 @@ UI-TARS Desktop is a GUI Agent application based on [UI-TARS (Vision-Language Mo
 | &nbsp&nbsp 👓 <a href="https://github.com/web-infra-dev/midscene">Midscene (use in browser)</a>
 </p>
 
+### ⚠️ Important Announcement: GGUF Model Performance
+
+The **GGUF model** has undergone quantization, but unfortunately, its performance cannot be guaranteed. As a result, we have decided to **downgrade** it. 
+
+💡 **Alternative Solution**:  
+You can use **[Cloud Deployment](#cloud-deployment)** or **[Local Deployment [vLLM]](#local-deployment-vllm)** instead. 
+
+We appreciate your understanding and patience as we work to ensure the best possible experience.
+
 ## Showcases
 
 | Instruction  | Video |
@@ -64,13 +73,41 @@ You can download the [latest release](https://github.com/bytedance/UI-TARS-deskt
 
 <img src="./images/windows_install.png" width="400px" />
 
-### Settings
+### Deployment
+
+### Cloud Deployment
+We recommend using HuggingFace Inference Endpoints for fast deployment.
+We provide two docs for users to refer:
+
+English version: [GUI Model Deployment Guide](https://juniper-switch-f10.notion.site/GUI-Model-Deployment-Guide-17b5350241e280058e98cea60317de71)
+
+中文版: [GUI模型部署教程](https://bytedance.sg.larkoffice.com/docx/TCcudYwyIox5vyxiSDLlgIsTgWf#U94rdCxzBoJMLex38NPlHL21gNb)
 
-#### VLM (Vision-Language Model)
+### Local Deployment [vLLM]
+We recommend using vLLM for fast deployment and inference. You need to use `vllm>=0.6.1`.
+```bash
+pip install -U transformers
+VLLM_VERSION=0.6.6
+CUDA_VERSION=cu124
+pip install vllm==${VLLM_VERSION} --extra-index-url https://download.pytorch.org/whl/${CUDA_VERSION}
+
+```
+#### Download the Model
+We provide three model sizes on Hugging Face: **2B**, **7B**, and **72B**. To achieve the best performance, we recommend using the **7B-DPO** or **72B-DPO** model (based on your hardware configuration):
+
+- [2B-SFT](https://huggingface.co/bytedance-research/UI-TARS-2B-SFT)
+- [7B-SFT](https://huggingface.co/bytedance-research/UI-TARS-7B-SFT)
+- [7B-DPO](https://huggingface.co/bytedance-research/UI-TARS-7B-DPO)
+- [72B-SFT](https://huggingface.co/bytedance-research/UI-TARS-72B-SFT)
+- [72B-DPO](https://huggingface.co/bytedance-research/UI-TARS-72B-DPO)
 
-We recommend using HuggingFace Inference Endpoints for fast deployment. We provide two docs for users to refer:
 
-[GUI Model Deployment Guide](https://juniper-switch-f10.notion.site/GUI-Model-Deployment-Guide-17b5350241e280058e98cea60317de71)
+#### Start an OpenAI API Service
+Run the command below to start an OpenAI-compatible API service:
+
+```bash
+python -m vllm.entrypoints.openai.api_server --served-model-name ui-tars --model <path to your model>
+```
 
 
 <img src="./images/settings_model.png" width="500px" />