mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
04de2f84e9
Each model known to the system has two identifiers: - the `provider_resource_id` (what the provider calls it) -- e.g., `accounts/fireworks/models/llama-v3p1-8b-instruct` - the `identifier` (`model_id`) under which it is registered and gets routed to the appropriate provider. We have so far used the HuggingFace repo alias as the standardized identifier you can use to refer to the model. So in the above example, we'd use `meta-llama/Llama-3.1-8B-Instruct` as the name under which it gets registered. This makes it convenient for users to refer to these models across providers. However, we forgot to register the _actual_ provider model ID also. You should be able to route via `provider_resource_id` also, of course. This change fixes this (somewhat grave) omission. *Note*: this change is additive -- more aliases work now compared to before. ## Test Plan Run the following for distro=(ollama fireworks together) ``` LLAMA_STACK_CONFIG=$distro \ pytest -s -v tests/client-sdk/inference/test_text_inference.py \ --inference-model=meta-llama/Llama-3.1-8B-Instruct --vision-inference-model="" ```
38 lines
1.2 KiB
Python
38 lines
1.2 KiB
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.models.llama.sku_list import CoreModelId
|
|
from llama_stack.providers.utils.inference.model_registry import (
|
|
build_hf_repo_model_entry,
|
|
build_model_entry,
|
|
)
|
|
|
|
MODEL_ENTRIES = [
|
|
build_hf_repo_model_entry(
|
|
"groq/llama3-8b-8192",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"groq/llama-3.1-8b-instant",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"groq/llama3-70b-8192",
|
|
CoreModelId.llama3_70b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"groq/llama-3.3-70b-versatile",
|
|
CoreModelId.llama3_3_70b_instruct.value,
|
|
),
|
|
# Groq only contains a preview version for llama-3.2-3b
|
|
# Preview models aren't recommended for production use, but we include this one
|
|
# to pass the test fixture
|
|
# TODO(aidand): Replace this with a stable model once Groq supports it
|
|
build_hf_repo_model_entry(
|
|
"groq/llama-3.2-3b-preview",
|
|
CoreModelId.llama3_2_3b_instruct.value,
|
|
),
|
|
]
|