Ahmadzei's picture
update 1
57bdca5
raw
history blame contribute delete
976 Bytes
For example, consider the following chat:
python
messages = [
{"role": "user", "content": "Hi there!"},
{"role": "assistant", "content": "Nice to meet you!"},
{"role": "user", "content": "Can I ask a question?"}
]
Here's what this will look like without a generation prompt, using the ChatML template we saw in the Zephyr example:
python
tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False)
"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
"""
And here's what it looks like with a generation prompt:
python
tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""
Note that this time, we've added the tokens that indicate the start of a bot response.