[GLM4.6v] Required changes for bumping up to transformer 5.x (#13229)

docs/advanced_features/separate_reasoning.ipynb

@@ -256,9 +256,7 @@
     "\n",
     "tokenizer = AutoTokenizer.from_pretrained(\"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B\")\n",
     "input = tokenizer.apply_chat_template(\n",
-    "    messages,\n",
-    "    tokenize=False,\n",
-    "    add_generation_prompt=True,\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "\n",
     "gen_url = f\"http://localhost:{port}/generate\"\n",
@@ -319,9 +317,7 @@
     "llm = sgl.Engine(model_path=\"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B\")\n",
     "tokenizer = AutoTokenizer.from_pretrained(\"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B\")\n",
     "input = tokenizer.apply_chat_template(\n",
-    "    messages,\n",
-    "    tokenize=False,\n",
-    "    add_generation_prompt=True,\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "sampling_params = {\n",
     "    \"max_new_tokens\": 1024,\n",

docs/advanced_features/structured_outputs.ipynb

@@ -443,7 +443,7 @@
     "    }\n",
     "]\n",
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
@@ -525,7 +525,7 @@
     "    }\n",
     "]\n",
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
@@ -571,7 +571,7 @@
     "    }\n",
     "]\n",
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
@@ -606,7 +606,7 @@
     "tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Meta-Llama-3.1-8B-Instruct\")\n",
     "\n",
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "payload = {\n",
     "    \"text\": text,\n",
@@ -883,7 +883,7 @@
    "outputs": [],
    "source": [
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "prompts = [text]\n",
     "\n",

docs/advanced_features/structured_outputs_for_reasoning_models.ipynb

@@ -400,7 +400,7 @@
     "    },\n",
     "]\n",
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "# Make API request\n",
     "response = requests.post(\n",
@@ -448,7 +448,7 @@
     "\n",
     "# JSON\n",
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "response = requests.post(\n",
     "    f\"http://localhost:{port}/generate\",\n",
@@ -543,7 +543,7 @@
    "outputs": [],
    "source": [
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "payload = {\n",
     "    \"text\": text,\n",
@@ -765,7 +765,7 @@
    "outputs": [],
    "source": [
     "text = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=False, add_generation_prompt=True\n",
+    "    messages, tokenize=False, add_generation_prompt=True, return_dict=False\n",
     ")\n",
     "prompts = [text]\n",
     "\n",

docs/advanced_features/tool_parser.ipynb

@@ -391,10 +391,7 @@
     "messages = get_messages()\n",
     "\n",
     "input = tokenizer.apply_chat_template(\n",
-    "    messages,\n",
-    "    tokenize=False,\n",
-    "    add_generation_prompt=True,\n",
-    "    tools=tools,\n",
+    "    messages, tokenize=False, add_generation_prompt=True, tools=tools, return_dict=False\n",
     ")\n",
     "\n",
     "gen_url = f\"http://localhost:{port}/generate\"\n",
@@ -459,7 +456,7 @@
     "llm = sgl.Engine(model_path=\"Qwen/Qwen2.5-7B-Instruct\")\n",
     "tokenizer = llm.tokenizer_manager.tokenizer\n",
     "input_ids = tokenizer.apply_chat_template(\n",
-    "    messages, tokenize=True, add_generation_prompt=True, tools=tools\n",
+    "    messages, tokenize=True, add_generation_prompt=True, tools=tools, return_dict=False\n",
     ")\n",
     "\n",
     "# Note that for gpt-oss tool parser, adding \"no_stop_trim\": True\n",

docs/basic_usage/native_api.ipynb

@@ -410,7 +410,7 @@
     "]\n",
     "\n",
     "tokenizer = AutoTokenizer.from_pretrained(\"Skywork/Skywork-Reward-Llama-3.1-8B-v0.2\")\n",
-    "prompts = tokenizer.apply_chat_template(CONVS, tokenize=False)\n",
+    "prompts = tokenizer.apply_chat_template(CONVS, tokenize=False, return_dict=False)\n",
     "\n",
     "url = f\"http://localhost:{port}/classify\"\n",
     "data = {\"model\": \"Skywork/Skywork-Reward-Llama-3.1-8B-v0.2\", \"text\": prompts}\n",