scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 83

fix(ollama_chat.py): fix token counting

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-06 22:18:46 -08:00
parent 2bc710d8e9
commit 73d8e3e640
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/ollama_chat.py
View file

@ -230,7 +230,7 @@ def get_ollama_response(
model_response["model"] = "ollama/" + model
prompt_tokens = response_json.get("prompt_eval_count", litellm.token_counter(messages=messages)) # type: ignore
completion_tokens = response_json.get(
"eval_count", litellm.token_counter(text=response_json["message"])
"eval_count", litellm.token_counter(text=response_json["message"]["content"])
)
model_response["usage"] = litellm.Usage(
prompt_tokens=prompt_tokens,