From 4d58d29f8eb499328bcc80a431a3e869ab387720 Mon Sep 17 00:00:00 2001
From: Zuellni <123005779+Zuellni@users.noreply.github.com>
Date: Wed, 31 Jul 2024 01:25:02 +0200
Subject: [PATCH] Fix attention size typo

---
 exllama.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/exllama.py b/exllama.py
index 167e02e..6163cf8 100644
--- a/exllama.py
+++ b/exllama.py
@@ -78,7 +78,7 @@ class Loader:
 
             if self.config.max_input_len > max_seq_len:
                 self.config.max_input_len = max_seq_len
-                self.config.max_attention_len = max_seq_len**2
+                self.config.max_attention_size = max_seq_len**2
 
         self.tokenizer = ExLlamaV2Tokenizer(self.config)
         return (self,)