Create README.md

README.md

@@ -0,0 +1,44 @@
+---
+license: apache-2.0
+language:
+- zh
+- en
+pipeline_tag: text-generation
+library_name: transformers
+---
+<div align="center">
+<img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img> 
+</div>
+
+## Usage
+### Prebuilt [mlx-lm](https://github.com/ml-explore/mlx-lm.git)
+```bash
+pip install mlx-lm
+```
+### Inference
+```python
+from mlx_lm import load, generate
+model_path = "MiniCPM4.1-8B-MLX "
+model, tokenizer = load(model_path)
+messages = [{"role": "user", "content": "北京有什么好玩的地方？"}]
+# if open think mode, use the following code
+# prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+# if close think mode, use the following code
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False, enable_thinking=False)
+response = generate(
+    model=model,
+    tokenizer=tokenizer, 
+    prompt=prompt,
+    max_tokens=1500
+)
+print(response)
+```
+
+<p align="center">
+<a href="https://github.com/OpenBMB/MiniCPM/" target="_blank">GitHub Repo</a> |
+<a href="https://arxiv.org/abs/2506.07900" target="_blank">Technical Report</a> |
+<a href="https://mp.weixin.qq.com/s/KIhH2nCURBXuFXAtYRpuXg?poc_token=HBIsUWijxino8oJ5s6HcjcfXFRi0Xj2LJlxPYD9c">Join Us</a>
+</p>
+<p align="center">
+👋 Contact us in <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a>
+</p>