phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 12:21:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

clean up router inference

Browse source
This commit is contained in:
Xi Yan 2024-09-19 21:53:27 -07:00
parent f6146f8e58
commit 5d3c02d0fb
2 changed files with 5 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/apis/inference/client.py
View file

@ -93,7 +93,7 @@ async def run_main(host: str, port: int, stream: bool):
cprint(f"User>{message.content}", "green")
iterator = client.chat_completion(
ChatCompletionRequest(
model="Meta-Llama3.1-8B",
model="Meta-Llama3.1-8B-Instruct",
messages=[message],
stream=stream,
)
@ -104,7 +104,7 @@ async def run_main(host: str, port: int, stream: bool):
cprint(f"User>{message.content}", "green")
iterator = client.chat_completion(
ChatCompletionRequest(
model="Meta-Llama3.1-8B-Instruct",
model="Meta-Llama3.1-8B",
messages=[message],
stream=stream,
)