autoevaluate/roberta-base-squad2

Uso en Haystack

reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2")
# o
reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")

Para un ejemplo completo del uso de roberta-base-squad2 para la Respuesta a Preguntas, consulte los Tutoriales en la Documentación de Haystack.

Uso en Transformers

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/roberta-base-squad2"

# a) Obtener predicciones
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
'question': 'Why is model conversion important?',
'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Cargar modelo y tokenizador
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Hiperparámetros

batch_size = 96
n_epochs = 2
base_LM_model = "roberta-base"
max_seq_len = 386
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64