mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
7505b3cadf
* add TheoremQA with 5-shot * add huggingface_above_v4_33 classes * use num_worker partitioner in cli * update theoremqa * update TheoremQA * add TheoremQA * rename theoremqa -> TheoremQA * update TheoremQA output path * rewrite many model configs * update huggingface * further update * refine configs * update configs * update configs * add configs/eval_llama3_instruct.py * add summarizer multi faceted * update bbh datasets * update configs/models/hf_llama/lmdeploy_llama3_8b_instruct.py * rename class * update readme * update hf above v4.33
96 lines
3.5 KiB
Python
96 lines
3.5 KiB
Python
import json
|
|
import os
|
|
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class winograndeDataset(BaseDataset):
|
|
"""Disconnect from Huggingface, winograndeDataset."""
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
path = os.path.join(path, 'dev.jsonl')
|
|
dataset_list = []
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
prompt = line['sentence']
|
|
continue_prompt = prompt.split('_')[1]
|
|
data_item = {
|
|
'prompt': prompt,
|
|
'only_option1': line['option1'],
|
|
'only_option2': line['option2'],
|
|
'opt1': prompt.replace('_', line['option1']),
|
|
'opt2': prompt.replace('_', line['option2']),
|
|
'answer': line['answer'],
|
|
'cont': continue_prompt,
|
|
}
|
|
dataset_list.append(data_item)
|
|
dataset_list = Dataset.from_list(dataset_list)
|
|
return dataset_list
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class winograndeDataset_V2(BaseDataset):
|
|
"""Disconnect from Huggingface, winograndeDataset_V2."""
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
path = os.path.join(path, 'dev.jsonl')
|
|
dataset_list = []
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
prompt = line['sentence']
|
|
continue_prompt = prompt.split('_')[1]
|
|
answer = line['answer']
|
|
answer = ' AB'[int(answer)] if answer != '' else 'NULL'
|
|
data_item = {
|
|
'prompt': prompt,
|
|
'only_option1': line['option1'],
|
|
'only_option2': line['option2'],
|
|
'opt1': prompt.replace('_', line['option1']),
|
|
'opt2': prompt.replace('_', line['option2']),
|
|
'answer': answer,
|
|
'cont': continue_prompt,
|
|
}
|
|
dataset_list.append(data_item)
|
|
dataset_list = Dataset.from_list(dataset_list)
|
|
return dataset_list
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class winograndeDataset_V3(BaseDataset):
|
|
"""Disconnect from Huggingface, winograndeDataset_V2."""
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
dataset_dict = DatasetDict()
|
|
for split in ['train_xs', 'dev']:
|
|
filename = os.path.join(path, f'{split}.jsonl')
|
|
dataset_list = []
|
|
with open(filename, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
prompt = line['sentence']
|
|
continue_prompt = prompt.split('_')[1]
|
|
answer = line['answer']
|
|
answer = ' AB'[int(answer)] if answer != '' else 'NULL'
|
|
data_item = {
|
|
'prompt': prompt,
|
|
'only_option1': line['option1'],
|
|
'only_option2': line['option2'],
|
|
'opt1': prompt.replace('_', line['option1']),
|
|
'opt2': prompt.replace('_', line['option2']),
|
|
'answer': answer,
|
|
'cont': continue_prompt,
|
|
}
|
|
dataset_list.append(data_item)
|
|
dataset_dict[split] = Dataset.from_list(dataset_list)
|
|
return dataset_dict
|