yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-08-13 19:21:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated get_max_token_limit with latest models and numbers (#972)

Browse Source 
* Updated with latest models and numbers

* Updated as per comments.

* Added common Azure deployment names for models.

---------

Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
This commit is contained in:
afourney 2023-12-17 19:06:41 -08:00 committed by GitHub
parent 42e07ca836
commit b29f9a90e8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 27 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
autogen/token_count_utils.py
View File

@ -2,27 +2,33 @@ from typing import List, Union, Dict
import logging import logging
import json import json
import tiktoken import tiktoken
import re
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
def get_max_token_limit(model="gpt-3.5-turbo-0613"): def get_max_token_limit(model="gpt-3.5-turbo-0613"):
# Handle common azure model names/aliases
model = re.sub(r"^gpt\-?35", "gpt-3.5", model)
model = re.sub(r"^gpt4", "gpt-4", model)
max_token_limit = { max_token_limit = {
"gpt-3.5-turbo": 4096, "gpt-3.5-turbo": 4096,
"gpt-3.5-turbo-0301": 4096, "gpt-3.5-turbo-0301": 4096,
"gpt-3.5-turbo-0613": 4096, "gpt-3.5-turbo-0613": 4096,
"gpt-3.5-turbo-instruct": 4096, "gpt-3.5-turbo-instruct": 4096,
"gpt-3.5-turbo-16k": 16384, "gpt-3.5-turbo-16k": 16385,
"gpt-35-turbo": 4096, "gpt-3.5-turbo-16k-0613": 16385,
"gpt-35-turbo-16k": 16384, "gpt-3.5-turbo-1106": 16385,
"gpt-35-turbo-instruct": 4096,
"gpt-4": 8192, "gpt-4": 8192,
"gpt-4-32k": 32768, "gpt-4-32k": 32768,
"gpt-4-32k-0314": 32768, # deprecate in Sep "gpt-4-32k-0314": 32768, # deprecate in Sep
"gpt-4-0314": 8192, # deprecate in Sep "gpt-4-0314": 8192, # deprecate in Sep
"gpt-4-0613": 8192, "gpt-4-0613": 8192,
"gpt-4-32k-0613": 32768, "gpt-4-32k-0613": 32768,
"gpt-4-1106-preview": 128000,
"gpt-4-vision-preview": 128000,
} }
return max_token_limit[model] return max_token_limit[model]

20
test/test_token_count.py
View File

@ -1,4 +1,10 @@
from autogen.token_count_utils import count_token, num_tokens_from_functions, token_left, percentile_used from autogen.token_count_utils import (
count_token,
num_tokens_from_functions,
token_left,
percentile_used,
get_max_token_limit,
)
import pytest import pytest
func1 = { func1 = {
@ -67,6 +73,14 @@ def test_count_token():
assert percentile_used(text) == 10 / 4096 assert percentile_used(text) == 10 / 4096
def test_model_aliases():
assert get_max_token_limit("gpt35-turbo") == get_max_token_limit("gpt-3.5-turbo")
assert get_max_token_limit("gpt-35-turbo") == get_max_token_limit("gpt-3.5-turbo")
assert get_max_token_limit("gpt4") == get_max_token_limit("gpt-4")
assert get_max_token_limit("gpt4-32k") == get_max_token_limit("gpt-4-32k")
if __name__ == "__main__": if __name__ == "__main__":
test_num_tokens_from_functions() # test_num_tokens_from_functions()
test_count_token() # test_count_token()
test_model_aliases()