mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-15 17:44:01 +00:00
6b8a8c1be9
- fireworks, together do not support Llama-guard 3 8b model anymore - Need to default to ollama - current safety shields logic was not correct since the shield_id was the provider ( which had duplicates ) - Followed similar logic to models Note: Seems a bit over-engineered but this can now be extended to other providers and fits in the overall mechanism of how env_vars are used to manage starter. ### How to test ``` ENABLE_OLLAMA=ollama ENABLE_FIREWORKS=fireworks SAFETY_MODEL=llama-guard3:1b pytest -s -v tests/integration/ --stack-config starter -k 'not(supervised_fine_tune or builtin_tool_code or safety_with_image or code_interpreter_for or rag_and_code or truncation or register_and_unregister)' --text-model fireworks/meta-llama/Llama-3.3-70B-Instruct --vision-model fireworks/meta-llama/Llama-4-Scout-17B-16E-Instruct --safety-shield llama-guard3:1b --embedding-model all-MiniLM-L6-v2 ``` ### Related but not obvious in this PR In the llama-stack-ops repo, we run tests before publishing packages and docker containers. The actions in that repo were using the fireworks / together distros ( which are non-existent ) So need to update that to run with `starter` and use `ollama` specifically for safety.
106 lines
3 KiB
Python
106 lines
3 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.models.llama.sku_types import CoreModelId
|
|
from llama_stack.providers.utils.inference.model_registry import (
|
|
ProviderModelEntry,
|
|
build_hf_repo_model_entry,
|
|
build_model_entry,
|
|
)
|
|
|
|
SAFETY_MODELS_ENTRIES = [
|
|
# The Llama Guard models don't have their full fp16 versions
|
|
# so we are going to alias their default version to the canonical SKU
|
|
build_hf_repo_model_entry(
|
|
"llama-guard3:8b",
|
|
CoreModelId.llama_guard_3_8b.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama-guard3:1b",
|
|
CoreModelId.llama_guard_3_1b.value,
|
|
),
|
|
]
|
|
|
|
MODEL_ENTRIES = [
|
|
build_hf_repo_model_entry(
|
|
"llama3.1:8b-instruct-fp16",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"llama3.1:8b",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama3.1:70b-instruct-fp16",
|
|
CoreModelId.llama3_1_70b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"llama3.1:70b",
|
|
CoreModelId.llama3_1_70b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama3.1:405b-instruct-fp16",
|
|
CoreModelId.llama3_1_405b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"llama3.1:405b",
|
|
CoreModelId.llama3_1_405b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama3.2:1b-instruct-fp16",
|
|
CoreModelId.llama3_2_1b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"llama3.2:1b",
|
|
CoreModelId.llama3_2_1b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama3.2:3b-instruct-fp16",
|
|
CoreModelId.llama3_2_3b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"llama3.2:3b",
|
|
CoreModelId.llama3_2_3b_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama3.2-vision:11b-instruct-fp16",
|
|
CoreModelId.llama3_2_11b_vision_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"llama3.2-vision:latest",
|
|
CoreModelId.llama3_2_11b_vision_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama3.2-vision:90b-instruct-fp16",
|
|
CoreModelId.llama3_2_90b_vision_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"llama3.2-vision:90b",
|
|
CoreModelId.llama3_2_90b_vision_instruct.value,
|
|
),
|
|
build_hf_repo_model_entry(
|
|
"llama3.3:70b",
|
|
CoreModelId.llama3_3_70b_instruct.value,
|
|
),
|
|
ProviderModelEntry(
|
|
provider_model_id="all-minilm:l6-v2",
|
|
aliases=["all-minilm"],
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 384,
|
|
"context_length": 512,
|
|
},
|
|
),
|
|
ProviderModelEntry(
|
|
provider_model_id="nomic-embed-text",
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 768,
|
|
"context_length": 8192,
|
|
},
|
|
),
|
|
] + SAFETY_MODELS_ENTRIES
|