From d4c06684481be22d58543773d48d01f32e236a49 Mon Sep 17 00:00:00 2001
From: Kareem <81531392+KareemMusleh@users.noreply.github.com>
Date: Mon, 17 Mar 2025 05:19:58 +0700
Subject: [PATCH] fix (#2051)

---
 unsloth/models/llama.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index b2fbf0d07f..07805271f5 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -1548,7 +1548,7 @@ def unsloth_fast_generate(
         if "input_ids" in kwargs and kwargs["input_ids"] is not None and "max_new_tokens" in kwargs:
             if kwargs["input_ids"].shape[-1] + kwargs["max_new_tokens"] > self.config.max_position_embeddings:
                 raise ValueError(
-                    f'Unsloth: input length {kwargs["input_ids"].shape[-1]} + max_new_tokens {kwargs["max_new_tokens"]} exceeds the maximum sequence length of {model.config.max_position_embeddings}!\n'\
+                    f'Unsloth: input length {kwargs["input_ids"].shape[-1]} + max_new_tokens {kwargs["max_new_tokens"]} exceeds the maximum sequence length of {self.config.max_position_embeddings}!\n'\
                     'You will need to do long context extension by increasing the `max_seq_length` in `FastLanguageModel.from_pretrained`.'
                 )
     pass