phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(feat) add model_response.usage.completion_tokens for bedrock, palm, petals, sagemaker

Browse source
This commit is contained in:
ishaan-jaff 2023-10-27 09:51:50 -07:00
parent 97d237a896
commit 194f85e92f
4 changed files with 12 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/llms/bedrock.py
View file

@ -392,11 +392,9 @@ def completion(
model_response["created"] = time.time()
model_response["model"] = model
model_response["usage"] = {
"prompt_tokens": prompt_tokens,
"completion_tokens": completion_tokens,
"total_tokens": prompt_tokens + completion_tokens,
}
model_response.usage.completion_tokens = completion_tokens
model_response.usage.prompt_tokens = prompt_tokens
model_response.usage.total_tokens = prompt_tokens + completion_tokens
return model_response

8
litellm/llms/palm.py
View file

@ -157,11 +157,9 @@ def completion(
model_response["created"] = time.time()
model_response["model"] = "palm/" + model
model_response["usage"] = {
"prompt_tokens": prompt_tokens,
"completion_tokens": completion_tokens,
"total_tokens": prompt_tokens + completion_tokens,
}
model_response.usage.completion_tokens = completion_tokens
model_response.usage.prompt_tokens = prompt_tokens
model_response.usage.total_tokens = prompt_tokens + completion_tokens
return model_response
def embedding():

8
litellm/llms/petals.py
View file

@ -176,11 +176,9 @@ def completion(
model_response["created"] = time.time()
model_response["model"] = model
model_response["usage"] = {
"prompt_tokens": prompt_tokens,
"completion_tokens": completion_tokens,
"total_tokens": prompt_tokens + completion_tokens,
}
model_response.usage.completion_tokens = completion_tokens
model_response.usage.prompt_tokens = prompt_tokens
model_response.usage.total_tokens = prompt_tokens + completion_tokens
return model_response
def embedding():

8
litellm/llms/sagemaker.py
View file

@ -169,11 +169,9 @@ def completion(
model_response["created"] = time.time()
model_response["model"] = model
model_response["usage"] = {
"prompt_tokens": prompt_tokens,
"completion_tokens": completion_tokens,
"total_tokens": prompt_tokens + completion_tokens,
}
model_response.usage.completion_tokens = completion_tokens
model_response.usage.prompt_tokens = prompt_tokens
model_response.usage.total_tokens = prompt_tokens + completion_tokens
return model_response
def embedding():