phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix: llama4 tool use prompt fix (#2103)

Browse source 
Tests:
LLAMA_STACK_CONFIG=http://localhost:5002 pytest -s -v
tests/integration/inference --safety-shield meta-llama/Llama-Guard-3-8B
--vision-model meta-llama/Llama-4-Scout-17B-16E-Instruct --text-model
meta-llama/Llama-4-Scout-17B-16E-Instruct

LLAMA_STACK_CONFIG=http://localhost:5002 pytest -s -v
tests/integration/inference --safety-shield meta-llama/Llama-Guard-3-8B
--vision-model Llama-4-Maverick-17B-128E-Instruct --text-model
Llama-4-Maverick-17B-128E-Instruct

Co-authored-by: Eric Huang <erichuang@fb.com>
This commit is contained in:
ehhuang 2025-05-06 22:18:31 -07:00 • committed by GitHub
parent b2b00a216b
commit 664161c462
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 9 additions and 203 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/models/llama/llama4/prompt_format.md
View file

@ -173,9 +173,7 @@ INCORRECT: [get_events(location="Singapore")] <- If function not in list
- Don't repeat tool response verbatim
- Don't add supplementary information
Here is a list of functions in JSON format that you can invoke.
Here is a list of functions in JSON format that you can invoke:
[
{
"name": "get_weather",
@ -196,10 +194,7 @@ Here is a list of functions in JSON format that you can invoke.
}
}
}
]
You can answer general questions or invoke tools when necessary.
In addition to tool calls, you should also augment your responses by using the tool outputs.<|eot|><|header_start|>user<|header_end|>
]<|eot|><|header_start|>user<|header_end|>
What is the weather in SF and Seattle?<|eot|><|header_start|>assistant<|header_end|>