Update README.md

README.md

@@ -12,6 +12,7 @@ base_model:
 
 ## Example
 ### Q&A 1：
+<pre style="white-space: pre-wrap; word-break: break-all;">
 ```
 Describe the principle of QLORA, and supplement the corresponding latex formula and Python code implementation.
 ```
@@ -34,7 +35,7 @@ $$L(\theta) = \frac{1}{2} \sum_{i=1}^N ||\mathbf{x}_i - \mathbf{q}_i||^2$$
 where $L(\theta)$ is the loss function, $\theta$ is the neural network's parameters, $\mathbf{x}_i$ is the original audio signal, $\mathbf{q}_i$ is the quantized representation, and $N$ is the number of audio samples.
 
 Here's a simple Python code implementation using the Keras library:
-```python
+'''python
 import numpy as np
 from keras.models import Sequential
 from keras.layers import Conv2D, MaxPooling2D, Flatten
@@ -74,15 +75,18 @@ new_audio =...  # Load the new audio signal
 encoded_new_audio = encode_audio(new_audio)
 quantized_new_audio = np.round(encoded_new_audio)
 print(loss_function(new_audio, quantized_new_audio))
-```
+'''
 Note that this is a simplified example, and in practice, you would need to consider additional factors such as audio normalization, data augmentation, and regularization techniques to improve the performance of the QLORA model.
-
 ```
+</pre>
+
 
 ### Q&A 2：
+<pre style="white-space: pre-wrap; word-break: break-all;">
 ```
 解释什么是Transformer，使用中文回答。
 ```
 ```
 机器学习中的Transformer是一种深度学习模型，它主要用于自然语言处理和机器翻译领域。它的主要特点是使用自注意力机制（Self-Attention Mechanism），可以同时处理序列中的所有元素，而不是像传统的RNN模型那样，逐步处理。
-```
+```
+</pre>