phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 15:23:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

for inline make 8b model the default

Browse source
This commit is contained in:
Hardik Shah 2024-08-08 10:45:32 -07:00
parent 8d7ecf0c47
commit ad9eaf13bb
1 changed files with 6 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_toolchain/inference/meta_reference/config.py
View file

@ -11,14 +11,17 @@ from llama_models.datatypes import ModelFamily
from llama_models.schema_utils import json_schema_type
from llama_models.sku_list import all_registered_models
from pydantic import BaseModel, validator
from llama_toolchain.inference.api import QuantizationConfig
from pydantic import BaseModel, Field, validator
@json_schema_type
class MetaReferenceImplConfig(BaseModel):
model: str
model: str = Field(
default="Meta-Llama3.1-8B-Instruct",
description="Model descriptor from `llama model list`",
)
quantization: Optional[QuantizationConfig] = None
torch_seed: Optional[int] = None
max_seq_len: int