phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 09:21:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Move to 3_2 format

Browse source
This commit is contained in:
Aidan Do 2024-12-20 08:58:45 +11:00
parent 4331796692
commit c20f342cde
1 changed files with 4 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/utils/inference/prompt_adapter.py
View file

@ -271,17 +271,13 @@ def chat_completion_request_to_messages(
log.error(f"Unsupported inference model? {model.descriptor()}")
return request.messages
if (
model.model_family == ModelFamily.llama3_1
or (
model.model_family == ModelFamily.llama3_2
and is_multimodal(model.core_model_id)
)
or model.model_family == ModelFamily.llama3_3
if model.model_family == ModelFamily.llama3_1 or (
model.model_family == ModelFamily.llama3_2
and is_multimodal(model.core_model_id)
):
# llama3.1, llama3.2 multimodal and llama3.3 models follow the same tool prompt format
messages = augment_messages_for_tools_llama_3_1(request)
elif model.model_family == ModelFamily.llama3_2:
elif model.model_family in (ModelFamily.llama3_2, ModelFamily.llama3_3):
messages = augment_messages_for_tools_llama_3_2(request)
else:
messages = request.messages