Better Qwen2.5-VL chat template.

Author: alcoftTAO

llama_cpp/llama_chat_format.py

@@ -3465,33 +3465,53 @@ class Qwen25VLChatHandler(Llava15ChatHandler):
     DEFAULT_SYSTEM_MESSAGE = "You are a helpful assistant."
 
     CHAT_FORMAT = (
-        #"{% set image_count = namespace(value=0) %}"
-        #"{% set video_count = namespace(value=0) %}"
-        "{% for message in messages %}"
-        "{% 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'] }}<|im_end|>\n"
-        "{% else %}"
-        "{% for content in message['content'] %}"
-        "{% 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 %}"
-        "<|im_end|>\n"
-        "{% endif %}"
-        "{% endfor %}"
-        "<|im_start|>assistant\n"
+        "{%- set image_count = namespace(value=0) -%}"
+        "{%- for message in messages -%}"
+            "{%- if loop.first and message[\"role\"] != \"system\" -%}"
+                "{{- \"<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n\" -}}"
+            "{%- endif -%}"
+            "{{- \"<|im_start|>\" -}}"
+            "{{- message[\"role\"] -}}"
+            "{{- \"\n\" -}}"
+            "{%- if message[\"content\"] is string -%}"
+                "{{- message[\"content\"] -}}"
+                "{{- \"<|im_end|>\n\" -}}"
+            "{%- else -%}"
+                "{%- for content in message[\"content\"] -%}"
+                    "{%- if content[\"type\"] == \"image\" or \"image\" in content -%}"
+                        "{%- set image_count.value = image_count.value + 1 -%}"
+                        "{%- if add_vision_id -%}"
+                            "{{- \"Picture \" -}}"
+                            "{{- image_count.value -}}"
+                            "{{- \": \" -}}"
+                        "{%- endif -%}"
+                        "{{- \"<|vision_start|>\" -}}"
+                            "{{- content.image -}}"
+                        "{{- \"<|vision_end|>\" -}}"
+                    "{%- elif content[\"type\"] == \"image_url\" or \"image_url\" in content -%}"
+                        "{%- set image_count.value = image_count.value + 1 -%}"
+                        "{%- if add_vision_id -%}"
+                            "{{- \"Picture \" -}}"
+                            "{{- image_count.value -}}"
+                            "{{- \": \" -}}"
+                        "{%- endif -%}"
+                        "{{- \"<|vision_start|>\" -}}"
+                            "{%- if content.image_url is string -%}"
+                                "{{- content.image_url -}}"
+                            "{%- else -%}"
+                                "{{- content.image_url.url -}}"
+                            "{%- endif -%}"
+                        "{{- \"<|vision_end|>\" -}}"
+                    "{%- elif \"text\" in content -%}"
+                        "{{- content[\"text\"] -}}"
+                    "{%- endif -%}"
+                "{%- endfor -%}"
+                "{{- \"<|im_end|>\n\" -}}"
+            "{%- endif -%}"
+        "{%- endfor -%}"
+        "{%- if add_generation_prompt -%}"
+            "{{- \"<|im_start|>assistant\n\" -}}"
+        "{%- endif -%}"
     )
 
     def __call__(self, **kwargs):