cleanup, add chat template

chat_template.jinja

@@ -0,0 +1,131 @@
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is mapping %}
+                    {%- for args_name in tool_call.arguments %}
+                        {%- set args_value = tool_call.arguments[args_name] %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-  "size": {
-    "longest_edge": 16777216,
-    "shortest_edge": 65536
-  },
-  "patch_size": 16,
-  "temporal_patch_size": 2,
-  "merge_size": 2,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "processor_class": "Qwen3VLProcessor",
-  "image_processor_type": "Qwen2VLImageProcessorFast"
-}

processor_config.json

@@ -1,63 +0,0 @@
-{
-  "image_processor": {
-    "data_format": "channels_first",
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "image_mean": [
-      0.5,
-      0.5,
-      0.5
-    ],
-    "image_processor_type": "Qwen2VLImageProcessorFast",
-    "image_std": [
-      0.5,
-      0.5,
-      0.5
-    ],
-    "merge_size": 2,
-    "patch_size": 16,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "longest_edge": 16777216,
-      "shortest_edge": 65536
-    },
-    "temporal_patch_size": 2
-  },
-  "processor_class": "Qwen3VLProcessor",
-  "video_processor": {
-    "data_format": "channels_first",
-    "default_to_square": true,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "do_sample_frames": true,
-    "fps": 2,
-    "image_mean": [
-      0.5,
-      0.5,
-      0.5
-    ],
-    "image_std": [
-      0.5,
-      0.5,
-      0.5
-    ],
-    "max_frames": 768,
-    "merge_size": 2,
-    "min_frames": 4,
-    "patch_size": 16,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "return_metadata": false,
-    "size": {
-      "longest_edge": 25165824,
-      "shortest_edge": 4096
-    },
-    "temporal_patch_size": 2,
-    "video_processor_type": "Qwen3VLVideoProcessor"
-  }
-}

video_preprocessor_config.json

@@ -1,21 +0,0 @@
-{
-    "size": {
-        "longest_edge": 25165824,
-        "shortest_edge": 4096
-    },
-    "patch_size": 16,
-    "temporal_patch_size": 2,
-    "merge_size": 2,
-    "image_mean": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "image_std": [
-        0.5,
-        0.5,
-        0.5
-    ],
-    "processor_class": "Qwen3VLProcessor",
-    "video_processor_type": "Qwen3VLVideoProcessor"
-}