Update README.md to be more detailed

README.md

@@ -70,6 +70,7 @@ The **LongRoPE** model architecture is designed to extend the context window of
 The LongRoPE model extends the context window of large language models beyond 2 million tokens. Key components include:
 
 1. Rotary Position Encoding (RoPE):
+
    ```python
    class RoPEPositionalEncoding(nn.Module):
        def __init__(self, d_model, max_len=1000000, base=10000):
@@ -85,6 +86,7 @@ The LongRoPE model extends the context window of large language models beyond 2
            return sin_cos.view(*sin_cos.shape[:-2], -1)
 
 2. Non-uniform Interpolation:
+
   ```python
   def non_uniform_interpolation(pos_embed, extension_ratio, lambda_factors, n_hat):
     d_model = pos_embed.shape[-1]
@@ -97,6 +99,7 @@ The LongRoPE model extends the context window of large language models beyond 2
         interpolated_pos[..., 2 * i + 1] *= scale
     return interpolated_pos
 
+
 ### Progressive Extension Strategy
 
 The architecture begins with a pre-trained LLM and extends its context window incrementally. Initially, the model is fine-tuned to handle a context length of 256k tokens. This progressive approach avoids the need for direct fine-tuning on extremely long texts, which are rare and computationally expensive to process. By gradually increasing the context length, the model can adapt more effectively to longer sequences.