mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-08-02 03:32:50 +08:00
df63f05b47
* fix dataloader * add test case * fix type * fix ci * fix ci * fix ci * disable overwrite cache in ci Former-commit-id: 8c3f9f6747110107cbbb3695637482e45084dbc1
61 lines
2.3 KiB
Python
61 lines
2.3 KiB
Python
# Copyright 2025 the LlamaFactory team.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from llamafactory.data import Role
|
|
from llamafactory.data.converter import get_dataset_converter
|
|
from llamafactory.data.parser import DatasetAttr
|
|
from llamafactory.hparams import DataArguments
|
|
|
|
|
|
def test_alpaca_converter():
|
|
dataset_attr = DatasetAttr("hf_hub", "llamafactory/tiny-supervised-dataset")
|
|
data_args = DataArguments()
|
|
example = {
|
|
"instruction": "Solve the math problem.",
|
|
"input": "3 + 4",
|
|
"output": "The answer is 7.",
|
|
}
|
|
dataset_converter = get_dataset_converter("alpaca", dataset_attr, data_args)
|
|
assert dataset_converter(example) == {
|
|
"_prompt": [{"role": Role.USER.value, "content": "Solve the math problem.\n3 + 4"}],
|
|
"_response": [{"role": Role.ASSISTANT.value, "content": "The answer is 7."}],
|
|
"_system": "",
|
|
"_tools": "",
|
|
"_images": None,
|
|
"_videos": None,
|
|
"_audios": None,
|
|
}
|
|
|
|
|
|
def test_sharegpt_converter():
|
|
dataset_attr = DatasetAttr("hf_hub", "llamafactory/tiny-supervised-dataset")
|
|
data_args = DataArguments()
|
|
example = {
|
|
"conversations": [
|
|
{"from": "system", "value": "You are a helpful assistant."},
|
|
{"from": "human", "value": "Solve the math problem.\n3 + 4"},
|
|
{"from": "gpt", "value": "The answer is 7."},
|
|
]
|
|
}
|
|
dataset_converter = get_dataset_converter("sharegpt", dataset_attr, data_args)
|
|
assert dataset_converter(example) == {
|
|
"_prompt": [{"role": Role.USER.value, "content": "Solve the math problem.\n3 + 4"}],
|
|
"_response": [{"role": Role.ASSISTANT.value, "content": "The answer is 7."}],
|
|
"_system": "You are a helpful assistant.",
|
|
"_tools": "",
|
|
"_images": None,
|
|
"_videos": None,
|
|
"_audios": None,
|
|
}
|