forked from phoenix-oss/llama-stack-mirror
a626b7bce3
# What does this PR do? create a new dataset BFCL_v3 from https://gorilla.cs.berkeley.edu/blogs/13_bfcl_v3_multi_turn.html overall each question asks the model to perform a task described in natural language, and additionally a set of available functions and their schema are given for the model to choose from. the model is required to write the function call form including function name and parameters , to achieve the stated purpose. the results are validated against provided ground truth, to make sure that the generated function call and the ground truth function call are syntactically and semantically equivalent, by checking their AST . ## Test Plan start server by ``` llama stack run ./llama_stack/templates/ollama/run.yaml ``` then send traffic ``` llama-stack-client eval run-benchmark "bfcl" --model-id meta-llama/Llama-3.2-3B-Instruct --output-dir /tmp/gpqa --num-examples 2 ``` [//]: # (## Documentation)
28 lines
904 B
Python
28 lines
904 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 typing import List
|
|
|
|
from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec
|
|
|
|
|
|
def available_providers() -> List[ProviderSpec]:
|
|
return [
|
|
InlineProviderSpec(
|
|
api=Api.eval,
|
|
provider_type="inline::meta-reference",
|
|
pip_packages=["tree_sitter"],
|
|
module="llama_stack.providers.inline.eval.meta_reference",
|
|
config_class="llama_stack.providers.inline.eval.meta_reference.MetaReferenceEvalConfig",
|
|
api_dependencies=[
|
|
Api.datasetio,
|
|
Api.datasets,
|
|
Api.scoring,
|
|
Api.inference,
|
|
Api.agents,
|
|
],
|
|
),
|
|
]
|