phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 14:57:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

resource oriented object design for models

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-07 16:43:55 -08:00
parent 5625aef48a
commit ca88f3f182
17 changed files with 63 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -16,7 +16,7 @@ from llama_models.sku_list import all_registered_models
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.apis.models import * # noqa: F403
from llama_stack.providers.datatypes import ModelDef, ModelsProtocolPrivate
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
@ -50,14 +50,14 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
if model.huggingface_repo
}
async def register_model(self, model: ModelDef) -> None:
raise ValueError("Model registration is not supported for HuggingFace models")
async def register_model(self, model: Model) -> None:
pass
async def list_models(self) -> List[ModelDef]:
async def list_models(self) -> List[Model]:
repo = self.model_id
identifier = self.huggingface_repo_to_llama_model_id[repo]
return [
ModelDef(
Model(
identifier=identifier,
llama_model=identifier,
metadata={