Update README.md

README.md

@@ -13,6 +13,35 @@ The Model [fastx-ai/Marco-o1-int-4](https://huggingface.co/fastx-ai/Marco-o1-int
 converted to MLX format from [AIDC-AI/Marco-o1](https://huggingface.co/AIDC-AI/Marco-o1)
 using mlx-lm version **0.20.1**.
 
+```python
+prompt="hello, can you teach me why 2 + 4 = 6 ?"
+```
+
+```shell
+==========
+Prompt: <|im_start|>system
+
+你是一个经过良好训练的AI助手，你的名字是Marco-o1.
+        
+## 重要！！！！！
+当你回答问题时，你的思考应该在<Thought>内完成，<Output>内输出你的结果。
+<Thought>应该尽可能是英文，但是有2个特例，一个是对原文中的引用，另一个是是数学应该使用markdown格式，<Output>内的输出需要遵循用户输入的语言。
+        <|im_end|>
+<|im_start|>user
+hello, can you teach me why 2 + 4 = 6 ?<|im_end|>
+<|im_start|>assistant
+
+<Thought>
+Alright, I need to explain why 2 plus 4 equals 6. Let's start by recalling the basic principles of addition. Addition is the process of combining two or more numbers to find their total. So, when we add 2 and 4, we're essentially combining two quantities.
+
+First, let's visualize this. Imagine you have 2 apples and someone gives you 4 more apples. Now, how many apples do you have in total? Counting them out
+==========
+Prompt: 118 tokens, 698.640 tokens-per-sec
+Generation: 100 tokens, 103.937 tokens-per-sec
+Peak memory: 4.386 GB
+
+```
+
 ## Use with mlx
 
 ```bash
@@ -22,7 +51,7 @@ pip install mlx-lm
 ```python
 from mlx_lm import load, generate
 
-model, tokenizer = load("fastx-ai/Marco-o1-int-4")
+model, tokenizer = load("fastx-ai/Marco-o1-1.2B-mlx-int4")
 
 prompt="hello"