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

[Feat] Add max_completion_tokens param (#5691)

Browse source 
* add max_completion_tokens

* add max_completion_tokens

* add max_completion_tokens support for OpenAI models

* add max_completion_tokens param

* add max_completion_tokens for bedrock converse models

* add test for converse maxTokens

* fix openai o1 param mapping test

* move test optional params

* add max_completion_tokens for anthropic api

* fix conftest

* add max_completion tokens for vertex ai partner models

* add max_completion_tokens for fireworks ai

* add max_completion_tokens for hf rest api

* add test for param mapping

* add param mapping for vertex, gemini + testing

* predibase is the most unstable and unusable llm api in prod, can't handle our ci/cd

* add max_completion_tokens to openai supported params

* fix fireworks ai param mapping
This commit is contained in:
Ishaan Jaff 2024-09-14 14:57:01 -07:00 • committed by GitHub
parent 415a3ede9e
commit 85acdb9193
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
31 changed files with 591 additions and 35 deletions
Download patch file Download diff file Expand all files Collapse all files

3
litellm/llms/huggingface_restapi.py
View file

@ -139,6 +139,7 @@ class HuggingfaceConfig:
"stream",
"temperature",
"max_tokens",
"max_completion_tokens",
"top_p",
"stop",
"n",
@ -167,7 +168,7 @@ class HuggingfaceConfig:
optional_params["stream"] = value
if param == "stop":
optional_params["stop"] = value
if param == "max_tokens":
if param == "max_tokens" or param == "max_completion_tokens":
# HF TGI raises the following exception when max_new_tokens==0
# Failed: Error occurred: HuggingfaceException - Input validation error: `max_new_tokens` must be strictly positive
if value == 0: