phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 13:42:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

temp commit

Browse source
This commit is contained in:
Botao Chen 2024-12-12 21:44:03 -08:00
parent 8efe33646d
commit de44af1501
9 changed files with 153 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/inline/inference/meta_reference/config.py
View file

@ -10,16 +10,13 @@ from llama_models.datatypes import * # noqa: F403
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 pydantic import BaseModel, field_validator
from llama_stack.providers.utils.inference import supported_inference_models
class MetaReferenceInferenceConfig(BaseModel):
model: str = Field(
default="Llama3.2-3B-Instruct",
description="Model descriptor from `llama model list`",
)
model: Optional[str] = None
torch_seed: Optional[int] = None
max_seq_len: int = 4096
max_batch_size: int = 1