File size: 5,217 Bytes
db704cb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 |
# 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.
import random
import pytest
from datasets import load_dataset
from llamafactory.v1.config.data_args import DataArguments
from llamafactory.v1.core.data_engine import DataEngine
from llamafactory.v1.plugins.data_plugins.converter import DataConverterPlugin
@pytest.mark.parametrize("num_samples", [16])
def test_alpaca_converter(num_samples: int):
data_args = DataArguments(train_dataset="llamafactory/v1-dataset-info/tiny-supervised-dataset.yaml")
data_engine = DataEngine(data_args.train_dataset)
original_data = load_dataset("llamafactory/tiny-supervised-dataset", split="train")
indexes = random.choices(range(len(data_engine)), k=num_samples)
for index in indexes:
print(data_engine[index])
expected_data = {
"messages": [
{
"role": "user",
"content": [
{"type": "text", "value": original_data[index]["instruction"] + original_data[index]["input"]}
],
"loss_weight": 0.0,
},
{
"role": "assistant",
"content": [{"type": "text", "value": original_data[index]["output"]}],
"loss_weight": 1.0,
},
]
}
assert data_engine[index] == {"_dataset_name": "tiny_dataset", **expected_data}
def test_sharegpt_converter():
example = {
"conversations": [
{"from": "system", "value": "System"},
{"from": "human", "value": "User"},
{"from": "function_call", "value": "1"},
{"from": "observation", "value": "Observation"},
{"from": "gpt", "value": "Assistant"},
]
}
expected_data = {
"messages": [
{"role": "system", "content": [{"type": "text", "value": "System"}], "loss_weight": 0.0},
{"role": "user", "content": [{"type": "text", "value": "User"}], "loss_weight": 0.0},
{"role": "assistant", "content": [{"type": "tool_call", "value": "1"}], "loss_weight": 1.0},
{"role": "tool", "content": [{"type": "text", "value": "Observation"}], "loss_weight": 0.0},
{"role": "assistant", "content": [{"type": "text", "value": "Assistant"}], "loss_weight": 1.0},
]
}
assert DataConverterPlugin("sharegpt")(example) == expected_data
@pytest.mark.parametrize("num_samples", [16])
def test_pair_converter(num_samples: int):
data_args = DataArguments(train_dataset="llamafactory/v1-dataset-info/orca-dpo-pairs.yaml")
data_engine = DataEngine(data_args.train_dataset)
original_data = load_dataset("HuggingFaceH4/orca_dpo_pairs", split="train_prefs")
indexes = random.choices(range(len(data_engine)), k=num_samples)
for index in indexes:
print(data_engine[index])
print(original_data[index])
expected_data = {
"chosen_messages": [
{
"role": "system",
"content": [{"type": "text", "value": original_data[index]["chosen"][0]["content"]}],
"loss_weight": 0.0,
},
{
"role": "user",
"content": [{"type": "text", "value": original_data[index]["chosen"][1]["content"]}],
"loss_weight": 0.0,
},
{
"role": "assistant",
"content": [{"type": "text", "value": original_data[index]["chosen"][2]["content"]}],
"loss_weight": 1.0,
},
],
"rejected_messages": [
{
"role": "system",
"content": [{"type": "text", "value": original_data[index]["rejected"][0]["content"]}],
"loss_weight": 0.0,
},
{
"role": "user",
"content": [{"type": "text", "value": original_data[index]["rejected"][1]["content"]}],
"loss_weight": 0.0,
},
{
"role": "assistant",
"content": [{"type": "text", "value": original_data[index]["rejected"][2]["content"]}],
"loss_weight": 1.0,
},
],
}
assert data_engine[index] == {"_dataset_name": "tiny_dataset", **expected_data}
if __name__ == "__main__":
"""
python -m tests_v1.plugins.data_plugins.test_converter
"""
test_alpaca_converter(1)
test_sharegpt_converter()
test_pair_converter(1)
|