phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-31 16:01:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor

Browse source
This commit is contained in:
Xi Yan 2024-11-08 14:19:55 -08:00
parent 9d04f11543
commit 490f7e9a75
3 changed files with 8 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/inline/huggingface/datasetio/dataset_defs/__init__.py → llama_stack/providers/inline/huggingface/datasetio/benchmarks/__init__.py
View file

@ -3,3 +3,4 @@
# #
# This source code is licensed under the terms described in the LICENSE file in # This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree. # the root directory of this source tree.
from .llamastack_mmlu import llamastack_mmlu # noqa: F401

0
llama_stack/providers/inline/huggingface/datasetio/dataset_defs/llamastack_mmlu.py → llama_stack/providers/inline/huggingface/datasetio/benchmarks/llamastack_mmlu.py
View file

13
llama_stack/providers/inline/huggingface/datasetio/huggingface.py
View file

@ -8,24 +8,25 @@ from typing import List, Optional
from llama_stack.apis.datasetio import * # noqa: F403 from llama_stack.apis.datasetio import * # noqa: F403
from datasets import Dataset, load_dataset import datasets as hf_datasets
from llama_stack.providers.datatypes import DatasetsProtocolPrivate from llama_stack.providers.datatypes import DatasetsProtocolPrivate
from llama_stack.providers.utils.datasetio.url_utils import get_dataframe_from_url from llama_stack.providers.utils.datasetio.url_utils import get_dataframe_from_url
from .benchmarks import llamastack_mmlu
from .config import HuggingfaceDatasetIOConfig from .config import HuggingfaceDatasetIOConfig
from .dataset_defs.llamastack_mmlu import llamastack_mmlu
def load_hf_dataset(dataset_def: DatasetDef): def load_hf_dataset(dataset_def: DatasetDef):
if dataset_def.metadata.get("path", None): if dataset_def.metadata.get("path", None):
return load_dataset(**dataset_def.metadata) return hf_datasets.load_dataset(**dataset_def.metadata)
df = get_dataframe_from_url(dataset_def.url) df = get_dataframe_from_url(dataset_def.url)
if df is None: if df is None:
raise ValueError(f"Failed to load dataset from {dataset_def.url}") raise ValueError(f"Failed to load dataset from {dataset_def.url}")
dataset = Dataset.from_pandas(df) dataset = hf_datasets.Dataset.from_pandas(df)
return dataset return dataset
@ -37,8 +38,8 @@ class HuggingfaceDatasetIOImpl(DatasetIO, DatasetsProtocolPrivate):
async def initialize(self) -> None: async def initialize(self) -> None:
# pre-registered benchmark datasets # pre-registered benchmark datasets
self.pre_registered_datasets = [llamastack_mmlu] pre_registered_datasets = [llamastack_mmlu]
self.dataset_infos = {x.identifier: x for x in self.pre_registered_datasets} self.dataset_infos = {x.identifier: x for x in pre_registered_datasets}
async def shutdown(self) -> None: ... async def shutdown(self) -> None: ...