add qwen3 chat template

Author: MohdElgaar

open_instruct/dataset_transformation.py

@@ -660,6 +660,69 @@ def visualize_token_role(tokens: list[int], masks: list[int], tokenizer: PreTrai
         "{% endif %}"
         "{% endfor %}"
     ),
+    "qwen2.5": (
+        "{% if messages[0]['role'] == 'system' %}"
+        "{{ '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}"
+        "{% else %}"
+        "{{ '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}"
+        "{% endif %}"
+        "{% for message in messages %}"
+        "{% if message['role'] == 'user' or (message['role'] == 'system' and not loop.first) %}"
+        "{{ '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>\\n' }}"
+        "{% elif message['role'] == 'assistant' %}"
+        "{{ '<|im_start|>assistant\\n' + message['content'] }}"
+        "{% if not loop.last %}"
+        "{{ '<|im_end|>\\n' }}"
+        "{% else %}"
+        "{{ eos_token }}"
+        "{% endif %}"
+        "{% endif %}"
+        "{% if loop.last and add_generation_prompt %}"
+        "{{ '<|im_start|>assistant\\n' }}"
+        "{% endif %}"
+        "{% endfor %}"
+    ),
+    "qwen3": (
+        "{% if messages[0].role == 'system' %}"
+        "{{ '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}"
+        "{% endif %}"
+        "{% for message in messages %}"
+        "{% if message.content is string %}"
+        "{% set content = message.content %}"
+        "{% else %}"
+        "{% set content = '' %}"
+        "{% endif %}"
+        "{% if (message.role == 'user') or (message.role == 'system' and not loop.first) %}"
+        "{{ '<|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 %}"
+        "{% if loop.index0 > ns.last_query_index %}"
+        "{% if loop.last or (not loop.last and reasoning_content) %}"
+        "{{ '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}"
+        "{% else %}"
+        "{{ '<|im_start|>' + message.role + '\\n' + content }}"
+        "{% endif %}"
+        "{% else %}"
+        "{{ '<|im_start|>' + message.role + '\\n' + content }}"
+        "{% endif %}"
+        "{{ '<|im_end|>\\n' }}"
+        "{% endif %}"
+        "{% endfor %}"
+        "{% if add_generation_prompt %}"
+        "{{ '<|im_start|>assistant\\n' }}"
+        "{% if enable_thinking is defined and enable_thinking is false %}"
+        "{{ '<think>\\n\\n</think>\\n\\n' }}"
+        "{% endif %}"
+        "{% endif %}"
+    ),
 }
 # flake8: noqa