phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix fireworks and update the test

Browse source 
Don't look for eom_id / eot_id sadly since providers don't return the
last token
This commit is contained in:
Ashwin Bharambe 2024-10-07 17:43:47 -07:00 • committed by Ashwin Bharambe
parent bbd3a02615
commit dba7caf1d0
4 changed files with 37 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/providers/adapters/inference/together/together.py
View file

@ -64,17 +64,6 @@ class TogetherInferenceAdapter(
) -> AsyncGenerator:
raise NotImplementedError()
def _messages_to_together_messages(self, messages: list[Message]) -> list:
together_messages = []
for message in messages:
if message.role == "ipython":
role = "tool"
else:
role = message.role
together_messages.append({"role": role, "content": message.content})
return together_messages
def get_together_chat_options(self, request: ChatCompletionRequest) -> dict:
options = {}
if request.sampling_params is not None: