license: mit

I don't see the README content provided. Let me check if there's a README file in the workspace for this model. The README content field appears empty. Let me fetch the README directly from HuggingFace for this model. The HuggingFace README for this model only contains a license header (MIT). Let me check if there's a source file in the workspace with the full README content. I found a related file. Let me check the project structure to understand the source README location and see if there's a source file for this model. Let me check the project structure to understand where source READMEs are stored and look at an existing translation for reference. Let me check for source README files and also look at another similar model's translation to understand the full pattern. I see the pattern now. The user's message shows "README content:" but no content was provided. Let me fetch the README from HuggingFace for the specific model 01-ai_Yi-1.5-6B-Chat-int4-onnx-directml: The HuggingFace page shows "README.md exists but content is empty" for this model. Let me check a similar model's README to understand the expected structure: The README for EmbeddedLLM/01-ai_Yi-1.5-6B-Chat-int4-onnx-directml on HuggingFace is empty (only contains a license header). Your message also shows "README content:" without actual content.

Based on similar models in this collection, here's the translated README:

---
license: mit
language:
- en
pipeline_tag: text-generation
tags:
- pytorch
- ONNX
- DirectML
- DML
- conversational
- ONNXRuntime
- custom_code
---
# Yi-1.5-6B-Chat DirectML ONNX 模型 (INT4)

本仓库托管了 [01-ai/Yi-1.5-6B-Chat](https://huggingface.co/01-ai/Yi-1.5-6B-Chat) 的优化版本，用于加速 DirectML 的 ONNX Runtime 推理。

## Windows 上的使用方法 (Intel / AMD / Nvidia / Qualcomm)
```powershell
conda create -n onnx python=3.10
conda activate onnx
winget install -e --id GitHub.GitLFS
pip install huggingface-hub[cli]
huggingface-cli download EmbeddedLLM/01-ai_Yi-1.5-6B-Chat-int4-onnx-directml --local-dir .\01-ai_Yi-1.5-6B-Chat-int4
pip install numpy==1.26.4
Invoke-WebRequest -Uri "https://raw.githubusercontent.com/microsoft/onnxruntime-genai/main/examples/python/phi3-qa.py" -OutFile "phi3-qa.py"
pip install onnxruntime-directml
pip install --pre onnxruntime-genai-directml
conda install conda-forge::vs2015_runtime
python phi3-qa.py -m .\01-ai_Yi-1.5-6B-Chat-int4

什么是 DirectML

DirectML 是一个高性能、硬件加速的 DirectX 12 机器学习库。DirectML 为各种支持的硬件和驱动程序上的常见机器学习任务提供 GPU 加速，包括来自 AMD、Intel、NVIDIA 和 Qualcomm 等供应商的所有支持 DirectX 12 的 GPU。

Would you like me to save this to `readme_cn/EmbeddedLLM__01-ai_Yi-1.5-6B-Chat-int4-onnx-directml.md`, or do you have the actual README content you'd like me to translate instead?