From 36f8bd5ded5b3469f7892099590bb2405cc8f744 Mon Sep 17 00:00:00 2001
From: Driss Guessous <32754868+drisspg@users.noreply.github.com>
Date: Wed, 23 Oct 2024 10:15:03 -0700
Subject: [PATCH] Fix typo in readme (#64)

stack-info: PR: https://github.com/pytorch-labs/attention-gym/pull/64, branch: drisspg/stack/1
---
 README.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index cad6dea..3e0ecbf 100644
--- a/README.md
+++ b/README.md
@@ -34,7 +34,7 @@ cd attention-gym
 pip install .
 ```
 
-## 💻 Usage 
+## 💻 Usage
 
 There are two main ways to use Attention Gym:
 
@@ -48,10 +48,10 @@ There are two main ways to use Attention Gym:
    ```python
    from torch.nn.attention.flex_attention import flex_attention, create_block_mask
    from attn_gym.masks import generate_sliding_window
-   
+
    # Use the imported function in your code
-   sliding_window_mask = generate_sliding_window(window_size=1024)
-   block_mask = create_block_mask(mask_mod, 1, 1, S, S, device=device)
+   sliding_window_mask_mod = generate_sliding_window(window_size=1024)
+   block_mask = create_block_mask(sliding_window_mask_mod, 1, 1, S, S, device=device)
    out = flex_attention(query, key, value, block_mask=block_mask)
    ```