phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

datasetdef files

Browse source
This commit is contained in:
Xi Yan 2024-11-07 10:28:51 -08:00
parent d75095033d
commit b946afddc0
3 changed files with 29 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/inline/huggingface/datasetio/dataset_defs/__init__.py Normal file
View file

@ -0,0 +1,5 @@
# 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.

21
llama_stack/providers/inline/huggingface/datasetio/dataset_defs/llamastack_mmlu.py Normal file
View file

@ -0,0 +1,21 @@
# 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_models.llama3.api.datatypes import URL
from llama_stack.apis.common.type_system import StringType
from llama_stack.apis.datasetio import DatasetDef
llamastack_mmlu = DatasetDef(
identifier="llamastack_mmlu",
url=URL(uri="https://huggingface.co/datasets/yanxi0830/ls-mmlu"),
dataset_schema={
"expected_answer": StringType(),
"input_query": StringType(),
"generated_answer": StringType(),
},
metadata={"path": "yanxi0830/ls-mmlu", "split": "train"},
)

19
llama_stack/providers/inline/huggingface/datasetio/huggingface.py
View file

@ -5,16 +5,13 @@
# the root directory of this source tree.
from typing import List, Optional
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_stack.apis.datasetio import * # noqa: F403
from datasets import load_dataset
from llama_stack.apis.common.type_system import StringType
from llama_stack.providers.datatypes import DatasetsProtocolPrivate
from .config import HuggingfaceDatasetIOConfig
from .dataset_defs.llamastack_mmlu import llamastack_mmlu
class HuggingfaceDatasetIOImpl(DatasetIO, DatasetsProtocolPrivate):
@ -25,18 +22,8 @@ class HuggingfaceDatasetIOImpl(DatasetIO, DatasetsProtocolPrivate):
async def initialize(self) -> None:
# pre-registered benchmark datasets
self.dataset_infos = {
"mmlu": DatasetDef(
identifier="mmlu",
url=URL(uri="https://huggingface.co/datasets/yanxi0830/ls-mmlu"),
dataset_schema={
"expected_answer": StringType(),
"input_query": StringType(),
"generated_answer": StringType(),
},
metadata={"path": "yanxi0830/ls-mmlu", "split": "train"},
)
}
self.pre_registered_datasets = [llamastack_mmlu]
self.dataset_infos = {x.identifier: x for x in self.pre_registered_datasets}
async def shutdown(self) -> None: ...