mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
ac5fd57387
# What does this PR do? * Given that our API packages use "import *" in `__init.py__` we don't need to do `from llama_stack.apis.models.models` but simply from llama_stack.apis.models. The decision to use `import *` is debatable and should probably be revisited at one point. * Remove unneeded Ruff F401 rule * Consolidate Ruff F403 rule in the pyprojectfrom llama_stack.apis.models.models Signed-off-by: Sébastien Han <seb@redhat.com>
35 lines
1.1 KiB
Python
35 lines
1.1 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.apis.models import ModelType
|
|
from llama_stack.providers.utils.inference.model_registry import (
|
|
ProviderModelEntry,
|
|
)
|
|
|
|
LLM_MODEL_IDS = [
|
|
"anthropic/claude-3-5-sonnet-latest",
|
|
"anthropic/claude-3-7-sonnet-latest",
|
|
"anthropic/claude-3-5-haiku-latest",
|
|
]
|
|
|
|
|
|
MODEL_ENTRIES = [ProviderModelEntry(provider_model_id=m) for m in LLM_MODEL_IDS] + [
|
|
ProviderModelEntry(
|
|
provider_model_id="anthropic/voyage-3",
|
|
model_type=ModelType.embedding,
|
|
metadata={"embedding_dimension": 1024, "context_length": 32000},
|
|
),
|
|
ProviderModelEntry(
|
|
provider_model_id="anthropic/voyage-3-lite",
|
|
model_type=ModelType.embedding,
|
|
metadata={"embedding_dimension": 512, "context_length": 32000},
|
|
),
|
|
ProviderModelEntry(
|
|
provider_model_id="anthropic/voyage-code-3",
|
|
model_type=ModelType.embedding,
|
|
metadata={"embedding_dimension": 1024, "context_length": 32000},
|
|
),
|
|
]
|