From 4c31218f80e35c4d94097a792a15b7817381daf0 Mon Sep 17 00:00:00 2001 From: Reid <61492567+reidliu41@users.noreply.github.com> Date: Sat, 10 May 2025 21:23:31 +0800 Subject: [PATCH] [Misc] remove --model from vllm serve usage (#17944) Signed-off-by: reidliu41 Co-authored-by: reidliu41 --- .../openai_chat_completion_client_with_tools.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/online_serving/openai_chat_completion_client_with_tools.py b/examples/online_serving/openai_chat_completion_client_with_tools.py index c25203860ff3..94f9c1570586 100644 --- a/examples/online_serving/openai_chat_completion_client_with_tools.py +++ b/examples/online_serving/openai_chat_completion_client_with_tools.py @@ -7,12 +7,12 @@ IMPORTANT: for mistral, you must use one of the provided mistral tool call templates, or your own - the model default doesn't work for tool calls with vLLM See the vLLM docs on OpenAI server & tool calling for more details. -vllm serve --model mistralai/Mistral-7B-Instruct-v0.3 \ +vllm serve mistralai/Mistral-7B-Instruct-v0.3 \ --chat-template examples/tool_chat_template_mistral.jinja \ --enable-auto-tool-choice --tool-call-parser mistral OR -vllm serve --model NousResearch/Hermes-2-Pro-Llama-3-8B \ +vllm serve NousResearch/Hermes-2-Pro-Llama-3-8B \ --chat-template examples/tool_chat_template_hermes.jinja \ --enable-auto-tool-choice --tool-call-parser hermes """