Using Qwen3-4B-Thinking

from transformers import pipeline

pipe = pipeline("text-generation", model="Qwen/Qwen3-4B-Thinking-2507")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

[{'generated_text': [{'role': 'user', 'content': 'Who are you?'},
   {'role': 'assistant',
    'content': "Okay, the user asked, Who are you? I need to provide a clear and concise response. First, I should state my identity as Qwen, the large language model developed by Tongyi Lab. Next, I should mention my capabilities, such as answering questions, generating text, coding, and logical reasoning. It's important to highlight that I can handle multiple languages and is designed to be helpful and friendly. I should avoid technical jargon to keep it accessible. Also, I need to check if there's any specific context the user might have in mind, but since the question is straightforward, a general response should suffice. Let me make sure the response is structured well: start with who I am, then key features, and a friendly closing. Let me see... the user might be new to me, so keeping it simple and welcoming is key. Alright, time to put it all together in a natural, conversational tone.\n</think>\n\nI'm **Qwen**, a large language model developed by Tongyi Lab. I'm here to help with a wide range of tasks, including answering questions, writing stories, emails, scripts, logical reasoning, coding, and more. I can also express opinions and play games! Whether you need assistance with a problem or just want"}]}]