fix: Better chat format for Qwen2.5-VL (#2040)

Author: alcoftTAO

llama_cpp/llama_chat_format.py

@@ -3459,26 +3459,29 @@ class Qwen25VLChatHandler(Llava15ChatHandler):
     DEFAULT_SYSTEM_MESSAGE = "You are a helpful assistant."
 
     CHAT_FORMAT = (
-        "<|im_start|>system\n"
-        "You are a helpful assistant.<|im_end|>\n"
+        #"{% set image_count = namespace(value=0) %}"
+        #"{% set video_count = namespace(value=0) %}"
         "{% for message in messages %}"
-        "{% if message['role'] == 'user' %}"
-        "<|im_start|>user\n"
+        "{% if loop.first and message['role'] != 'system' %}"
+        "<|im_start|>system\n"
+        "{{ self.DEFAULT_SYSTEM_MESSAGE }}<|im_end|>\n"
+        "{% endif %}"
+        "<|im_start|>{{ message['role'] }}\n"
         "{% if message['content'] is string %}"
-        "{{ message['content'] }}"
+        "{{ message['content'] }}<|im_end|>\n"
         "{% else %}"
         "{% for content in message['content'] %}"
-        "{% if content['type'] == 'text' %}"
-        "{{ content['text'] }}"
-        "{% elif content['type'] == 'image_url' %}"
+        "{% if content['type'] == 'image_url' %}"
         "{% if content.image_url is string %}"
         "{{ content.image_url }}"
         "{% else %}"
         "{{ content.image_url.url }}"
         "{% endif %}"
+        #"{% set image_count.value = image_count.value + 1 %}"
+        "{% elif content['type'] == 'text' %}"
+        "{{ content['text'] }}"
         "{% endif %}"
         "{% endfor %}"
-        "{% endif %}"
         "<|im_end|>\n"
         "{% endif %}"
         "{% endfor %}"