mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-29 03:14:19 +00:00
71caa271ad
there are likely scenarios where admins of a stack only want to allow clients to fine-tune certain models, register certain models to be fine-tuned. etc introduce the post_training router and post_training_models as the associated type. A different model type needs to be used for inference vs post_training due to the structure of the router currently. Signed-off-by: Charlie Doern <cdoern@redhat.com>
23 lines
742 B
Python
23 lines
742 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 llama_stack.apis.models.models import ModelType
|
|
from llama_stack.providers.utils.inference.model_registry import (
|
|
ProviderModelEntry,
|
|
)
|
|
|
|
model_entries = [
|
|
ProviderModelEntry(
|
|
provider_model_id="ibm-granite/granite-3.3-8b-instruct",
|
|
aliases=["ibm-granite/granite-3.3-8b-instruct"],
|
|
model_type=ModelType.llm,
|
|
),
|
|
ProviderModelEntry(
|
|
provider_model_id="ibm-granite/granite-3.3-8b-instruct",
|
|
aliases=["ibm-granite/granite-3.3-8b-instruct"],
|
|
model_type=ModelType.llm,
|
|
),
|
|
]
|