From 3ed14b2cec0dfdad3f4b2831f2b4a86d11aef150 Mon Sep 17 00:00:00 2001
From: Andrej Karpathy <andrej.karpathy@gmail.com>
Date: Sun, 27 Mar 2022 17:48:05 +0100
Subject: [PATCH] i know it doesn't look like much, but this kwarg was not used
 lol :D

---
 mingpt/model.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mingpt/model.py b/mingpt/model.py
index b315a7f..f4cc661 100644
--- a/mingpt/model.py
+++ b/mingpt/model.py
@@ -58,7 +58,7 @@ class CausalSelfAttention(nn.Module):
                                      .view(1, 1, config.block_size, config.block_size))
         self.n_head = config.n_head
 
-    def forward(self, x, layer_past=None):
+    def forward(self, x):
         B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
 
         # calculate query, key, values for all heads in batch and move head forward to be the batch dim