MarcBrun's picture
Update README.md
de0a40a
|
raw
history blame
2.68 kB
metadata
language:
  - en
  - es
  - eu
datasets:
  - squad
widget:
  - text: >-
      Florence Nightingale, known for being the founder of modern nursing, was
      born in Florence, Italy, in 1820.
    question: When was Florence Nightingale born?
    example_title: English
  - text: >-
      El Tajo es el río más largo de la península ibérica, a la que atraviesa en
      su parte central, siguiendo un rumbo este-oeste, con una       leve
      inclinación hacia el suroeste, que se acentúa cuando llega a Portugal,
      donde recibe el nombre de Tejo.

      Nace en los montes Universales, en la sierra de Albarracín, sobre la rama
      occidental del sistema Ibérico y, después de recorrer 1007 km, llega al
      océano Atlántico en la ciudad de Lisboa. En su desembocadura forma el
      estuario del mar de la Paja, en el que vierte un caudal medio de 456 m³/s.
      En sus primeros 816 km atraviesa España, donde discurre por cuatro
      comunidades autónomas (Aragón, Castilla-La Mancha, Madrid y Extremadura) y
      un total de seis provincias (Teruel, Guadalajara, Cuenca, Madrid, Toledo y
      Cáceres).
    question: ¿Cuál es la longitud del Tajo?
    example_title: Español
  - text: >-
      Basajaun basoan bizi den euskal mitologiako izakia da, Kondaira batzuetan,
      Basandere du emaztetzat.
    question: Zer beste izen du Basajaunak?
    example_title: Euskara

Description

This is a basic implementation of the multilingual model "ixambert-base-cased", fine-tuned on SQuAD v1.1, that is able to answer basic factual questions in English, Spanish and Basque.

Outputs

The model outputs the answer to the question, the start and end positions of the answer in the original context, and a score for the probability for that span of text to be the correct answer. For example:

{'score': 0.9667195081710815, 'start': 101, 'end': 105, 'answer': '1820'}

How to use

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "MarcBrun/ixambert-finetuned-squad"

# To get predictions
context = "Florence Nightingale, known for being the founder of modern nursing, was born in Florence, Italy, in 1820"
question = "When was Florence Nightingale born?"
qa = pipeline("question-answering", model=model_name, tokenizer=model_name)
pred = qa(question=question,context=context)

# To load the model and tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Hyperparameters

batch_size = 8
n_epochs = 3
base_LM_model = "ixambert-base-cased"
learning_rate = 2e-5
optimizer = AdamW
lr_schedule = linear
max_seq_len = 384
doc_stride = 128