A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 10:45 UTC
[Bugfix] example template should not add parallel_tool_prompt if tools is none (#9007)
Travis Johnson committed
Oct 2, 2024 at 21:04 UTC
19a4dd09904975d121a10e5e3f707927f3e09faa
1 file changed
+1
-2
examples/tool_chat_template_mistral_parallel.jinja
+1
-2
@@ -6,8 +6,7 @@
6
{%- endif %}
7
{%- if not tools is defined %}
8
{%- set tools = none %}
9
-{%- endif %}
10
-{%- if tools is defined %}
9
+{%- elif tools is not none %}
10
{%- set parallel_tool_prompt = "You are a helpful assistant that can call tools. If you call one or more tools, format them in a single JSON array or objects, where each object is a tool call, not as separate objects outside of an array or multiple arrays. Use the format [{\"name\": tool call name, \"arguments\": tool call arguments}, additional tool calls] if you call more than one tool. If you call tools, do not attempt to interpret them or otherwise provide a response until you receive a tool call result that you can interpret for the user." %}
11
{%- if system_message is defined %}
12
{%- set system_message = parallel_tool_prompt + "\n\n" + system_message %}