scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-11 22:51:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 123

test: add more logging

Browse source
This commit is contained in:
Krrish Dholakia 2024-01-31 19:31:07 -08:00
parent a32639fa79
commit 9593df23c4
2 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
litellm/tests/test_model_max_token_adjust.py
View file

@ -15,6 +15,7 @@ litellm.drop_params = True
def test_completion_sagemaker():
litellm.set_verbose = True
response = completion(
model="sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4",
messages=[{"content": "Hello, how are you?", "role": "user"}],

1
litellm/utils.py
View file

@ -2220,6 +2220,7 @@ def client(original_function):
pass # allow call to fail normally
elif user_max_tokens + input_tokens > max_output_tokens:
user_max_tokens = max_output_tokens - input_tokens
print_verbose(f"user_max_tokens: {user_max_tokens}")
kwargs["max_tokens"] = user_max_tokens
except Exception as e:
print_verbose(f"Error while checking max token limit: {str(e)}")