phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 14:39:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add model type

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-09 12:45:11 -08:00
parent e0d5be41fe
commit 62890b3171
6 changed files with 77 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/utils/inference/model_registry.py
View file

@ -9,6 +9,7 @@ from typing import List, Optional
from llama_models.sku_list import all_registered_models
from llama_stack.apis.models.models import ModelType
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
from llama_stack.providers.utils.inference import (
@ -77,7 +78,13 @@ class ModelRegistryHelper(ModelsProtocolPrivate):
return None
async def register_model(self, model: Model) -> Model:
provider_resource_id = self.get_provider_model_id(model.provider_resource_id)
if model.model_type == ModelType.embedding_model:
# embedding models are always registered by their provider model id and does not need to be mapped to a llama model
provider_resource_id = model.provider_resource_id
else:
provider_resource_id = self.get_provider_model_id(
model.provider_resource_id
)
if provider_resource_id:
model.provider_resource_id = provider_resource_id
else: