phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

make default max tokens a controllable param

Browse source
This commit is contained in:
Krrish Dholakia 2023-08-02 19:59:25 -07:00
parent 6cd1960b82
commit a964e326f1
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/main.py
View file

@ -189,7 +189,7 @@ def completion(
if max_tokens != float('inf'):
max_tokens_to_sample = max_tokens
else:
max_tokens_to_sample = 300 # default in Anthropic docs https://docs.anthropic.com/claude/reference/client-libraries
max_tokens_to_sample = litellm.max_tokens # default in Anthropic docs https://docs.anthropic.com/claude/reference/client-libraries
## LOGGING
logging(model=model, input=prompt, azure=azure, additional_args={"max_tokens": max_tokens}, logger_fn=logger_fn)
## COMPLETION CALL