Question_generator / README.md
mohamedemam's picture
Update README.md
0c143aa verified
metadata
license: mit
datasets:
  - squad_v2
  - quac
language:
  - en
widget:
  - text: >-
      when: Lionel Andrés Messi[note 1] (Spanish pronunciation: [ljoˈnel anˈdɾes
      ˈmesi] (listen); born 24 June 1987), also known as Leo Messi, is an
      Argentine professional footballer who plays as a forward for and captains
      both Major League Soccer club Inter Miami and the Argentina national team.
      Widely regarded as one of the greatest players of all time, Messi has won
      a record seven Ballon d'Or awards[note 2] and a record six European Golden
      Shoes, and in 2020 he was named to the Ballon d'Or Dream Team. Until
      leaving the club in 2021, he had spent his entire professional career with
      Barcelona, where he won a club-record 34
  - text: >-
      where: Lionel Andrés Messi[note 1] (Spanish pronunciation: [ljoˈnel
      anˈdɾes ˈmesi] (listen); born 24 June 1987), also known as Leo Messi, is
      an Argentine professional footballer who plays as a forward for and
      captains both Major League Soccer club Inter Miami and the Argentina
      national team. Widely regarded as one of the greatest players of all time,
      Messi has won a record seven Ballon d'Or awards[note 2] and a record six
      European Golden Shoes, and in 2020 he was named to the Ballon d'Or Dream
      Team. Until leaving the club in 2021, he had spent his entire professional
      career with Barcelona, where he won a club-record 34
  - text: >-
      how: Lionel Andrés Messi[note 1] (Spanish pronunciation: [ljoˈnel anˈdɾes
      ˈmesi] (listen); born 24 June 1987), also known as Leo Messi, is an
      Argentine professional footballer who plays as a forward for and captains
      both Major League Soccer club Inter Miami and the Argentina national team.
      Widely regarded as one of the greatest players of all time, Messi has won
      a record seven Ballon d'Or awards[note 2] and a record six European Golden
      Shoes, and in 2020 he was named to the Ballon d'Or Dream Team. Until
      leaving the club in 2021, he had spent his entire professional career with
      Barcelona, where he won a club-record 34
  - text: >-
      what: Lionel Andrés Messi[note 1] (Spanish pronunciation: [ljoˈnel anˈdɾes
      ˈmesi] (listen); born 24 June 1987), also known as Leo Messi, is an
      Argentine professional footballer who plays as a forward for and captains
      both Major League Soccer club Inter Miami and the Argentina national team.
      Widely regarded as one of the greatest players of all time, Messi has won
      a record seven Ballon d'Or awards[note 2] and a record six European Golden
      Shoes, and in 2020 he was named to the Ballon d'Or Dream Team. Until
      leaving the club in 2021, he had spent his entire professional career with
      Barcelona, where he won a club-record 34
  - text: >-
      where: Egypt (Egyptian Arabic: مصر Maṣr Egyptian Arabic pronunciation:
      [mɑsˤr]), officially the Arab Republic of Egypt, is a transcontinental
      country spanning the northeast corner of Africa and the Sinai Peninsula in
      the southwest corner of Asia. It is bordered by the Mediterranean Sea to
      the north, the Gaza Strip of Palestine and Israel to the northeast, the
      Red Sea to the east, Sudan to the south, and Libya to the west. The Gulf
      of Aqaba in the northeast separates Egypt from Jordan and Saudi Arabia.
      Cairo is the capital and largest city of Egypt, while Alexandria, the
      second-largest city, is an important industrial and tourist hub at the
      Mediterranean coast.[11] At approximately 100 million inhabitants, Egypt
      is the 14th-most populated country in the world, and the third-most
      populated in Africa, behind Nigeria and Ethiopia.
  - text: >-
      where: There is evidence of rock carvings along the Nile terraces and in
      desert oases. In the 10th millennium BCE, a culture of hunter-gatherers
      and fishers was replaced by a grain-grinding culture. Climate changes or
      overgrazing around 8000 BCE began to desiccate the pastoral lands of
      Egypt, forming the Sahara. Early tribal peoples migrated to the Nile River
      where they developed a settled agricultural economy and more centralized
      society.
  - text: >-
      when: By about 6000 BCE, a Neolithic culture took root in the Nile
      Valley.[31] During the Neolithic era, several predynastic cultures
      developed independently in Upper and Lower Egypt. The Badarian culture and
      the successor Naqada series are generally regarded as precursors to
      dynastic Egypt. The earliest known Lower Egyptian site, Merimda, predates
      the Badarian by about seven hundred years. Contemporaneous Lower Egyptian
      communities coexisted with their southern counterparts for more than two
      thousand years. The earliest known evidence of Egyptian hieroglyphic
      inscriptions appeared during the predynastic period on Naqada III pottery
      vessels, dated to about 3200 BCE.[32]
  - text: >-
      whose : or the next three millennia. Egyptian culture flourished during
      this long period and remained distinctively Egyptian in its religion,
      arts, language and customs. The first two ruling dynasties of a unified
      Egypt set the stage for the Old Kingdom period, c. 2700–2200 BCE, which
      constructed many pyramids, most notably the Third Dynasty pyramid of
      Djoser and the Fourth Dynasty Giza pyramids.
  - text: >-
      who:The First Intermediate Period ushered in a time of political upheaval
      for about 150 years.[33] Stronger Nile floods and stabilisation of
      government, however, brought back renewed prosperity for the country in
      the Middle Kingdom c. 2040 BCE, reaching a peak during the reign of
      Pharaoh Amenemhat III. A second period of disunity heralded the arrival of
      the first foreign ruling dynasty in Egypt, that of the Semitic Hyksos. The
      Hyksos invaders took over much of Lower Egypt around 1650 BCE and founded
      a new capital at Avaris. They were driven out by an Upper Egyptian force
      led by Ahmose I, who founded the Eighteenth Dynasty and relocated the
      capital from Memphis to Thebes.
library_name: transformers
tags:
  - generate answers
  - question generator
  - generate text
  - nlp
  - dataset maker
  - flan t5
  - t5
  - extract quetions from context
  - extract quetion

Model Card for QA_GeneraToR

Excited 😄 to share with you my very first model 🤖 for generating question-answering datasets! This incredible model takes articles 📜 or web pages, and all you need to provide is a prompt and context. It works like magic ✨, generating both the question and the answer. The prompt can be anything – "what," "who," "where" ... etc ! 😅

I've harnessed the power of the flan-t5 model 🚀, which has truly elevated the quality of the results. You can find all the code and details in the repository right here: https://lnkd.in/dhE5s_qg

And guess what? I've even deployed the project, so you can experience the magic firsthand: https://lnkd.in/diq-d3bt ❤️

Join me on this exciting journey into #nlp, #textgeneration, #t5, #deeplearning, and #huggingface. Your feedback and collaboration are more than welcome! 🌟

my fine tuned model

This model is fine tuned to generate a question with answers from a context , why that can be very usful this can help you to generate a dataset from a book article any thing you would to make from it dataset and train another model on this dataset , give the model any context with pre prometed of quation you want + context and it will extarct question + answer for you this are promted i use [ "which", "how", "when", "where", "who", "whom", "whose", "why", "which", "who", "whom", "whose", "whereas", "can", "could", "may", "might", "will", "would", "shall", "should", "do", "does", "did", "is", "are", "am", "was", "were", "be", "being", "been", "have", "has", "had", "if", "is", "are", "am", "was", "were", "do", "does", "did", "can", "could", "will", "would", "shall", "should", "might", "may", "must", "may", "might", "must"]

orignal model info

drawing

Code

from transformers import AutoTokenizer, AutoModelForQuestionAnswering
model_name="mohamedemam/Question_generator"
def generate_question_answer(context, prompt, model_name="mohamedemam/Question_generator"):
  """
  Generates a question-answer pair using the provided context, prompt, and model.

  Args:
      context: String containing the text or URL of the source material.
      prompt: String starting with a question word (e.g., "what," "who").
      model_name: Optional string specifying the model name (default: google/flan-t5-base).

  Returns:
      A tuple containing the generated question and answer strings.
  """

  tokenizer = AutoTokenizer.from_pretrained(model_name)
  model = AutoModelForQuestionAnswering.from_pretrained(model_name)

  inputs = tokenizer(context, return_tensors="pt")
  with torch.no_grad():
    outputs = model(**inputs)

  start_scores, end_scores = outputs.start_logits, outputs.end_logits
  answer_start = torch.argmax(start_scores)
  answer_end = torch.argmax(end_scores) + 1  # Account for inclusive end index

  answer = tokenizer.convert_tokens_to_strings(tokenizer.convert_ids_to_tokens(inputs["input_ids"][answer_start:answer_end]))[0]
  question = f"{prompt} {answer}"  # Formulate the question using answer

  return question, answer

# Example usage
context = "The capital of France is Paris."
prompt = "What"
question, answer = generate_question_answer(context, prompt)
print(f"Question: {question}")
print(f"Answer: {answer}")