pip install transformers datasets evaluate

>>> from huggingface_hub import notebook_login

>>> notebook_login()

>>> from datasets import load_dataset

>>> squad = load_dataset("squad", split="train[:5000]")

>>> squad = squad.train_test_split(test_size=0.2)

>>> squad["train"][0]
{'answers': {'answer_start': [515], 'text': ['Saint Bernadette Soubirous']},
 'context': 'Architecturally, the school has a Catholic character. Atop the Main Building\'s gold dome is a golden statue of the Virgin Mary. Immediately in front of the Main Building and facing it, is a copper statue of Christ with arms upraised with the legend "Venite Ad Me Omnes". Next to the Main Building is the Basilica of the Sacred Heart. Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. It is a replica of the grotto at Lourdes, France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous in 1858. At the end of the main drive (and in a direct line that connects through 3 statues and the Gold Dome), is a simple, modern stone statue of Mary.',
 'id': '5733be284776f41900661182',
 'question': 'To whom did the Virgin Mary allegedly appear in 1858 in Lourdes France?',
 'title': 'University_of_Notre_Dame'
}

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")

>>> def preprocess_function(examples):
...     questions = [q.strip() for q in examples["question"]]
...     inputs = tokenizer(
...         questions,
...         examples["context"],
...         max_length=384,
...         truncation="only_second",
...         return_offsets_mapping=True,
...         padding="max_length",
...     )

...     offset_mapping = inputs.pop("offset_mapping")
...     answers = examples["answers"]
...     start_positions = []
...     end_positions = []

...     for i, offset in enumerate(offset_mapping):
...         answer = answers[i]
...         start_char = answer["answer_start"][0]
...         end_char = answer["answer_start"][0] + len(answer["text"][0])
...         sequence_ids = inputs.sequence_ids(i)

...         # Find the start and end of the context
...         idx = 0
...         while sequence_ids[idx] != 1:
...             idx += 1
...         context_start = idx
...         while sequence_ids[idx] == 1:
...             idx += 1
...         context_end = idx - 1

...         # If the answer is not fully inside the context, label it (0, 0)
...         if offset[context_start][0] > end_char or offset[context_end][1] < start_char:
...             start_positions.append(0)
...             end_positions.append(0)
...         else:
...             # Otherwise it's the start and end token positions
...             idx = context_start
...             while idx <= context_end and offset[idx][0] <= start_char:
...                 idx += 1
...             start_positions.append(idx - 1)

...             idx = context_end
...             while idx >= context_start and offset[idx][1] >= end_char:
...                 idx -= 1
...             end_positions.append(idx + 1)

...     inputs["start_positions"] = start_positions
...     inputs["end_positions"] = end_positions
...     return inputs

>>> tokenized_squad = squad.map(preprocess_function, batched=True, remove_columns=squad["train"].column_names)

>>> question = "How many programming languages does BLOOM support?"
>>> context = "BLOOM has 176 billion parameters and can generate text in 46 languages natural languages and 13 programming languages."

>>> from transformers import pipeline

>>> question_answerer = pipeline("question-answering", model="my_awesome_qa_model")
>>> question_answerer(question=question, context=context)
{'score': 0.2058267742395401,
 'start': 10,
 'end': 95,
 'answer': '176 billion parameters and can generate text in 46 languages natural languages and 13'}