Skip to content

Updated get_max_token_limit with latest models and numbers #972

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Dec 18, 2023
Merged

Updated get_max_token_limit with latest models and numbers #972

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
86f3d9b
Updated with latest models and numbers
afourney Dec 13, 2023
ccbd72e
Updated as per comments.
afourney Dec 15, 2023
4990e5b
Added common Azure deployment names for models.
afourney Dec 15, 2023
365c67d
Merge branch 'main' into update_max_token_limits
qingyun-wu Dec 18, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 10 additions & 4 deletions autogen/token_count_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,27 +2,33 @@
import logging
import json
import tiktoken
import re


logger = logging.getLogger(__name__)


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 = {
"gpt-3.5-turbo": 4096,
"gpt-3.5-turbo-0301": 4096,
"gpt-3.5-turbo-0613": 4096,
"gpt-3.5-turbo-instruct": 4096,
"gpt-3.5-turbo-16k": 16384,
"gpt-35-turbo": 4096,
"gpt-35-turbo-16k": 16384,
"gpt-35-turbo-instruct": 4096,
"gpt-3.5-turbo-16k": 16385,
"gpt-3.5-turbo-16k-0613": 16385,
"gpt-3.5-turbo-1106": 16385,
"gpt-4": 8192,
"gpt-4-32k": 32768,
"gpt-4-32k-0314": 32768, # deprecate in Sep
"gpt-4-0314": 8192, # deprecate in Sep
"gpt-4-0613": 8192,
"gpt-4-32k-0613": 32768,
"gpt-4-1106-preview": 128000,
"gpt-4-vision-preview": 128000,
}
return max_token_limit[model]

Expand Down
20 changes: 17 additions & 3 deletions test/test_token_count.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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

func1 = {
Expand Down Expand Up @@ -67,6 +73,14 @@ def test_count_token():
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__":
test_num_tokens_from_functions()
test_count_token()
# test_num_tokens_from_functions()
# test_count_token()
test_model_aliases()