From b06fbc968b980daa313687152114dd1bfd1edaa9 Mon Sep 17 00:00:00 2001
From: Caleb DeLeeuw <143902425+SolshineCode@users.noreply.github.com>
Date: Tue, 4 Aug 2026 00:34:30 -0700
Subject: [PATCH] convert : import bytes_to_unicode from convert_slow_tokenizer
 (#26217)

bytes_to_unicode was removed from transformers.models.gpt2.tokenization_gpt2
in huggingface/transformers#40936, but it had already been copied into
transformers.convert_slow_tokenizer in huggingface/transformers#30334
(transformers 4.54.1), so import it directly from there.

Applies the same fix to chatglm.py.
---
 conversion/chatglm.py | 2 +-
 conversion/qwen.py    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/conversion/chatglm.py b/conversion/chatglm.py
index 801913075d..d638550387 100644
--- a/conversion/chatglm.py
+++ b/conversion/chatglm.py
@@ -81,7 +81,7 @@ class ChatGLMModel(TextModel):
 
     @staticmethod
     def token_bytes_to_string(b):
-        from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode  # ty: ignore[unresolved-import]
+        from transformers.convert_slow_tokenizer import bytes_to_unicode
         byte_encoder = bytes_to_unicode()
         return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')])
 
diff --git a/conversion/qwen.py b/conversion/qwen.py
index 7e3d8c0d12..b4ae528bf2 100644
--- a/conversion/qwen.py
+++ b/conversion/qwen.py
@@ -18,7 +18,7 @@ class QwenModel(TextModel):
 
     @staticmethod
     def token_bytes_to_string(b):
-        from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode  # ty: ignore[unresolved-import]
+        from transformers.convert_slow_tokenizer import bytes_to_unicode
         byte_encoder = bytes_to_unicode()
         return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')])