llama-stack-mirror/llama_toolchain/inference/meta_reference/config.py
Ashwin Bharambe f27d629fe8 Reduce a bunch of dependencies from toolchain
Some improvements to the distribution install script
2024-08-07 21:55:07 -07:00

22 lines
596 B
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Optional
from llama_models.schema_utils import json_schema_type
from pydantic import BaseModel
from llama_toolchain.inference.api import QuantizationConfig
@json_schema_type
class MetaReferenceImplConfig(BaseModel):
model: str
quantization: Optional[QuantizationConfig] = None
torch_seed: Optional[int] = None
max_seq_len: int
max_batch_size: int = 1