[QA] 书生2模型有关chat_template的问题 about internlm HOT 5 CLOSED

你可以使用tokenizer的apply_chat_template接口来处理openai样式的input message，然后直接使用model的generate接口进行对话

chat = [{"role": "user", "content": "Hello! What's your name?"},
        {"role": "assistant", "content": "My name is InternLM2!"},
        {"role": "user", "content": "Nice to meet you InternLM2!"},]

# convert the chat history to a string for generation
chat_str = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
print(chat_str)

output：

<s><|im_start|>user
Hello! What's your name?<|im_end|>
<|im_start|>assistant
My name is InternLM2!<|im_end|>
<|im_start|>user
Nice to meet you InternLM2!<|im_end|>
<|im_start|>assistant

我们之后会更新示例里面的用法

from internlm.

This issue is marked as stale because it has been marked as invalid or awaiting response for 7 days without any further response. It will be closed in 7 days if the stale label is not removed or if there is no further response.

from internlm.

如何体验 function call 的功能？

from internlm.

This issue is marked as stale because it has been marked as invalid or awaiting response for 7 days without any further response. It will be closed in 7 days if the stale label is not removed or if there is no further response.

from internlm.

This issue is closed because it has been stale for 7 days. Please open a new issue if you have similar issues or you have any new updates now.

from internlm.