Duplicate from vinayakdev/qa-generator

Co-authored-by: Vinayak Dev <[email protected]>

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.sav filter=lfs diff=lfs merge=lfs -text
+hfmodel.sav filter=lfs diff=lfs merge=lfs -text
+electra_model.sav filter=lfs diff=lfs merge=lfs -text
+t5_model.sav filter=lfs diff=lfs merge=lfs -text

.streamlit/config.toml

@@ -0,0 +1,3 @@
+[theme]
+base="light"
+backgroundColor="#FFFFFF"

README.md

@@ -0,0 +1,14 @@
+---
+title: Qa Generator
+emoji: 😻
+colorFrom: indigo
+colorTo: yellow
+sdk: streamlit
+sdk_version: 1.15.2
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: vinayakdev/qa-generator
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,21 @@
+import streamlit as st
+import generator
+from generator import *
+import string
+
+st.info("On a large paragraph, less questions will be produced, for increased accuracy.\n")
+text_ar = st.text_area("Enter text:")
+col1, col2, col3 = st.columns([2,1,2])
+x = st.container()
+if(col2.button("Generate!")):
+    text_ar = text_ar.replace("\n", " ")
+    pairs = creator(text_ar)
+    for pair in pairs:
+        x.text(pair)
+    st.balloons()
+
+
+  
+
+
+

electra_model.sav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d99ce35fd30c98ca681be026c3ddb54f725e5a343535b503c07032611f1b72a
+size 54032204

generator.py

@@ -0,0 +1,140 @@
+import transformers
+from transformers import (
+    # Text2TextGenerationPipeline,
+    AutoModelForSeq2SeqLM as alwm,
+    # TokenClassificationPipeline,
+    # AutoModelForTokenClassification,
+    AutoModelForQuestionAnswering as amqa,
+    AutoTokenizer as att,
+    # BertTokenizer,
+    AlbertTokenizer,
+    # BertForQuestionAnswering,
+    # AlbertForQuestionAnswering,
+    # T5Config,
+    # T5ForConditionalGeneration, 
+    T5TokenizerFast,
+    PreTrainedTokenizer,
+    PreTrainedModel,
+    ElectraTokenizer as et,
+    # ElectraForQuestionAnswering
+)
+import torch
+import sentencepiece
+import string
+import numpy as np
+from transformers import pipeline
+# from transformers.pipelines import pipeline
+import pickle
+import streamlit as st
+
+# sq_tokenizer = att.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
+# sq_model = alwm.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
+# text= "The abolition of feudal privileges by the National Constituent Assembly on 4 August 1789 and the Declaration \\nof the Rights of Man and of the Citizen (La Déclaration des Droits de l'Homme et du Citoyen), drafted by Lafayette \\nwith the help of Thomas Jefferson and adopted on 26 August, paved the way to a Constitutional Monarchy \\n(4 September 1791 – 21 September 1792). Despite these dramatic changes, life at the court continued, while the situation \\nin Paris was becoming critical because of bread shortages in September. On 5 October 1789, a crowd from Paris descended upon Versailles \\nand forced the royal family to move to the Tuileries Palace in Paris, where they lived under a form of house arrest under \\nthe watch of Lafayette's Garde Nationale, while the Comte de Provence and his wife were allowed to reside in the \\nPetit Luxembourg, where they remained until they went into exile on 20 June 1791."
+# hftokenizer = pickle.load(open('models/hftokenizer.sav', 'rb'))
+# hfmodel = pickle.load(open('models/hfmodel.sav', 'rb'))
+
+def load_model():
+  hfm = pickle.load(open('hfmodel.sav','rb'))
+  hft = T5TokenizerFast.from_pretrained("t5-base")
+  model = pickle.load(open('model.sav','rb'))
+  tok = AlbertTokenizer.from_pretrained("ahotrod/albert_xxlargev1_squad2_512")
+  # return hfm, hft,tok, model
+  return hfm, hft, tok, model
+
+hfmodel, hftokenizer, tokenizer, model = load_model()
+
+def run_model(input_string, **generator_args):
+  generator_args = {
+  "max_length": 256,
+  "num_beams": 4,
+  "length_penalty": 1.5,
+  "no_repeat_ngram_size": 3,
+  "early_stopping": True,
+  }
+  # tokenizer = att.from_pretrained("ThomasSimonini/t5-end2end-question-generation")
+  input_string = "generate questions: " + input_string + " </s>"
+  input_ids = hftokenizer.encode(input_string, return_tensors="pt")
+  res = hfmodel.generate(input_ids, **generator_args)
+  output = hftokenizer.batch_decode(res, skip_special_tokens=True)
+  output = [item.split("<sep>") for item in output]
+  return output
+
+
+
+# al_tokenizer = att.from_pretrained("deepset/electra-base-squad2")
+# al_model = amqa.from_pretrained("deepset/electra-base-squad2")
+# al_model = pickle.load(open('models/al_model.sav', 'rb'))
+# al_tokenizer = pickle.load(open('models/al_tokenizer.sav', 'rb'))
+def QA(question, context):
+  # model_name="deepset/electra-base-squad2"
+  # nlp = pipeline("question-answering",model=model,tokenizer = tok)
+  # format = {
+  #     'question':question,
+  #     'context':context
+  # }
+  # res = nlp(format)
+  # output = f"{question}\n{string.capwords(res['answer'])}\n"
+  # return output
+  inputs = tokenizer(question, context, return_tensors="pt")
+  # Run the model, the deepset way
+  with torch.no_grad():
+    output = model(**inputs)
+  start_score = output.start_logits
+  end_score = output.end_logits
+  #Get the rel scores for the context, and calculate the most probable begginign using torch
+  start = torch.argmax(start_score)
+  end = torch.argmax(end_score)
+  #cinvert tokens to strings
+  # output = tokenizer.decode(input_ids[start:end+1], skip_special_tokens=True)
+  predict_answer_tokens = inputs.input_ids[0, start : end + 1]
+  output = tokenizer.decode(predict_answer_tokens, skip_special_tokens=True)
+  output = string.capwords(output)
+  if output.isspace() or len(output) == 0:
+    return f"Possible question : {question}\n Answer could not be generated accurately."
+  return f"Q. {question} \n Ans. {output}"
+# QA("What was the first C program","The first prgram written in C was Hello World")
+
+def gen_question(inputs):
+
+ questions = run_model(inputs)
+
+ return questions
+
+# string_query = "Hello World"
+# gen_question(f"answer: {string_query} context: The first C program said {string_query} ").  #The format of the query to generate questions
+
+def tokenize(inputs) :
+    inputs = hftokenizer.batch_encode_plus(
+        inputs, 
+        max_length=512,
+        add_special_tokens=True,
+        truncation=True,
+        # padding="max_length",
+        pad_to_max_length=True,
+        return_tensors="pt"
+    )
+    return inputs
+    
+def read_file(filepath_name):
+  with open(text, "r") as infile:
+    contents = infile.read()
+    context = contents.replace("\n", " ")
+  return context
+
+def create_string_for_generator(context):
+    gen_list = gen_question(context)
+    return (gen_list[0][0]).split('? ')
+
+def creator(context):
+  questions = create_string_for_generator(context)
+  # questions = questions.split('?')
+  pairs = []
+  for ques in questions:
+    pair = QA(ques,context)
+    if len(pair) == 0:
+        continue
+    pairs.append(pair)
+  return pairs
+# creator(""""Hello, World!" program by Brian Kernighan (1978).
+# A "Hello, World!" program is generally a computer program that ignores any input and outputs or displays a message similar to "Hello, World!". A small piece of code in most general-purpose programming languages, this program is used to illustrate a language's basic syntax. "Hello, World!" programs are often the first a student learns to write in a given language,[1] and they can also be used as a sanity check to ensure computer software intended to compile or run source code is correctly installed, and that its operator understands how to use it.
+# """)

hfmodel.sav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b8a0eaae4db9a1d63b7ae641f8a81a31776ac27ee326016d006a8f4a3f9265
+size 891674698

main.py

@@ -0,0 +1,8 @@
+import generator
+from generator import *
+
+
+
+context = str(input("Enter paragraph\n"))
+context.replace("\n", " ")
+creator(context)

model.sav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d343950c24e17fefdac3a0b288306de41127b9097774b01ff7fd0d5887ff6d
+size 823312585

requirements.txt

@@ -0,0 +1,5 @@
+numpy==1.24.1
+sentencepiece==0.1.97
+streamlit==1.16.0
+torch==1.13.1
+transformers==4.25.1

t5_model.sav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd85d72d50394f86c47cde298e698cdd1f6ef2c43267f40e2719bb3b5f9278ec
+size 242049035