phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 12:21:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

bugfixes

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-28 15:21:32 -07:00
parent 37ca22cda6
commit 23028e26ff
7 changed files with 83 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/impls/meta_reference/inference/config.py
View file

@ -7,12 +7,13 @@
from typing import Optional
from llama_models.datatypes import * # noqa: F403
from llama_models.sku_list import all_registered_models, resolve_model
from llama_models.sku_list import resolve_model
from llama_stack.apis.inference import * # noqa: F401, F403
from pydantic import BaseModel, Field, field_validator
from llama_stack.providers.utils.inference import supported_inference_models
class MetaReferenceImplConfig(BaseModel):
model: str = Field(
@ -27,12 +28,7 @@ class MetaReferenceImplConfig(BaseModel):
@field_validator("model")
@classmethod
def validate_model(cls, model: str) -> str:
permitted_models = [
m.descriptor()
for m in all_registered_models()
if m.model_family in {ModelFamily.llama3_1, ModelFamily.llama3_2}
or m.core_model_id == CoreModelId.llama_guard_3_8b
]
permitted_models = supported_inference_models()
if model not in permitted_models:
model_list = "\n\t".join(permitted_models)
raise ValueError(