前言:
ChatGPT如何计算token数?https://wtl4it.blog.csdn.net/article/details/135116493?spm=1001.2014.3001.5502https://wtl4it.blog.csdn.net/article/details/135116493?spm=1001.2014.3001.5502
GPT3.5\GPT4系列计算完整prompt token数的官方方法:
How to count tokens with tiktoken | OpenAI CookbookOpen-source examples and guides for building with the OpenAI API. Browse a collection of snippets, advanced techniques and walkthroughs. Share your own examples and guides.https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktokenhttps://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynbhttps://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
计算的代码如下:
python
def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
"""Return the number of tokens used by a list of messages."""
try:
encoding = tiktoken.encoding_for_model(model)
except KeyError:
print("Warning: model not found. Using cl100k_base encoding.")
encoding = tiktoken.get_encoding("cl100k_base")
if model in {
"gpt-3.5-turbo-0613",
"gpt-3.5-turbo-16k-0613",
"gpt-4-0314",
"gpt-4-32k-0314",
"gpt-4-0613",
"gpt-4-32k-0613",
}:
tokens_per_message = 3
tokens_per_name = 1
elif model == "gpt-3.5-turbo-0301":
tokens_per_message = 4 # every message follows <|start|>{role/name}\n{content}<|end|>\n
tokens_per_name = -1 # if there's a name, the role is omitted
elif "gpt-3.5-turbo" in model:
print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613")
elif "gpt-4" in model:
print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
return num_tokens_from_messages(messages, model="gpt-4-0613")
else:
raise NotImplementedError(
f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
)
num_tokens = 0
for message in messages:
num_tokens += tokens_per_message
for key, value in message.items():
num_tokens += len(encoding.encode(value))
if key == "name":
num_tokens += tokens_per_name
num_tokens += 3 # every reply is primed with <|start|>assistant<|message|>
return num_tokens