forked from phoenix-oss/llama-stack-mirror
314ee09ae3
llama-models should have extremely minimal cruft. Its sole purpose should be didactic -- show the simplest implementation of the llama models and document the prompt formats, etc. This PR is the complement to https://github.com/meta-llama/llama-models/pull/279 ## Test Plan Ensure all `llama` CLI `model` sub-commands work: ```bash llama model list llama model download --model-id ... llama model prompt-format -m ... ``` Ran tests: ```bash cd tests/client-sdk LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/ LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/ LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/ ``` Create a fresh venv `uv venv && source .venv/bin/activate` and run `llama stack build --template fireworks --image-type venv` followed by `llama stack run together --image-type venv` <-- the server runs Also checked that the OpenAPI generator can run and there is no change in the generated files as a result. ```bash cd docs/openapi_generator sh run_openapi_generator.sh ```
36 lines
1.1 KiB
Python
36 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 typing import List
|
|
|
|
from llama_stack.models.llama.datatypes import * # noqa: F403
|
|
from llama_stack.models.llama.sku_list import all_registered_models
|
|
|
|
|
|
def is_supported_safety_model(model: Model) -> bool:
|
|
if model.quantization_format != CheckpointQuantizationFormat.bf16:
|
|
return False
|
|
|
|
model_id = model.core_model_id
|
|
return model_id in [
|
|
CoreModelId.llama_guard_3_8b,
|
|
CoreModelId.llama_guard_3_1b,
|
|
CoreModelId.llama_guard_3_11b_vision,
|
|
]
|
|
|
|
|
|
def supported_inference_models() -> List[Model]:
|
|
return [
|
|
m
|
|
for m in all_registered_models()
|
|
if (
|
|
m.model_family in {ModelFamily.llama3_1, ModelFamily.llama3_2, ModelFamily.llama3_3}
|
|
or is_supported_safety_model(m)
|
|
)
|
|
]
|
|
|
|
|
|
ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTOR = {m.huggingface_repo: m.descriptor() for m in all_registered_models()}
|