Here is the code
`from transformers import AutoTokenizer, AutoModelForQuestionAnswering
from transformers import squad_convert_examples_to_features
from transformers.data.processors.squad import SquadV2Processor
import torch
Load the SQuAD dataset
processor = SquadV2Processor()
train_examples = processor.get_train_examples(‘train/’)
dev_examples = processor.get_dev_examples(‘train/’)
Load the GPT-2 model and tokenizer
model_name = ‘gpt2’
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForQuestionAnswering.from_pretrained(model_name).to(‘cuda’)
Convert examples to features
train_features = squad_convert_examples_to_features(
examples=train_examples,
tokenizer=tokenizer,
max_seq_length=384,
doc_stride=128,
max_query_length=64,
is_training=True,
return_dataset=‘pt’,
threads=6
)
dev_features = squad_convert_examples_to_features(
examples=dev_examples,
tokenizer=tokenizer,
max_seq_length=384,
doc_stride=128,
max_query_length=64,
is_training=False,
return_dataset=‘pt’,
threads=6
)
Fine-tune the GPT-2 model on the SQuAD dataset
from transformers import Trainer, TrainingArguments
training_args = TrainingArguments(
output_dir=‘./results’,
evaluation_strategy=‘epoch’,
num_train_epochs=3,
per_device_train_batch_size=16,
per_device_eval_batch_size=16,
warmup_steps=500,
weight_decay=0.01,
logging_dir=‘./logs’,
)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_features,
eval_dataset=dev_features,
).to(‘cuda’)
trainer.train()
`
And here is the full error message
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 442/442 [00:34<00:00, 12.78it/s] 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 35/35 [00:03<00:00, 10.88it/s] Traceback (most recent call last): File "c:\Users\moroz\Desktop\train_ai\import torch.py", line 14, in <module> model = AutoModelForQuestionAnswering.from_pretrained(model_name).to('cuda') File "C:\Users\moroz\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\models\auto\auto_factory.py", line 467, in from_pretrained raise ValueError( ValueError: Unrecognized configuration class <class 'transformers.models.gpt2.configuration_gpt2.GPT2Config'> for this kind of AutoModel: AutoModelForQuestionAnswering. Model type should be one of AlbertConfig, BartConfig, BertConfig, BigBirdConfig, BigBirdPegasusConfig, BloomConfig, CamembertConfig, CanineConfig, ConvBertConfig, Data2VecTextConfig, DebertaConfig, DebertaV2Config, DistilBertConfig, ElectraConfig, ErnieConfig, FlaubertConfig, FNetConfig, FunnelConfig, GPTJConfig, IBertConfig, LayoutLMv2Config, LayoutLMv3Config, LEDConfig, LiltConfig, LongformerConfig, LukeConfig, LxmertConfig, MarkupLMConfig, MBartConfig, MegatronBertConfig, MobileBertConfig, MPNetConfig, MvpConfig, NezhaConfig, NystromformerConfig, OPTConfig, QDQBertConfig, ReformerConfig, RemBertConfig, RobertaConfig, RobertaPreLayerNormConfig, RoCBertConfig, RoFormerConfig, SplinterConfig, SqueezeBertConfig, XLMConfig, XLMRobertaConfig, XLMRobertaXLConfig, XLNetConfig, YosoConfig.
Can someone help me fix this problem or tell me how to teach GPT-2 (locally on my pc) for Q&A with ready-to-use dataset?
