Avinash250325 commited on
Commit
1217b67
·
verified ·
1 Parent(s): f6b78d5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -1
README.md CHANGED
@@ -74,7 +74,10 @@ Educational tools, tutoring platforms, and self-learning systems need a way to *
74
 
75
  ### Bonus: Retrieval-Augmented Generation (RAG)
76
 
77
- A **custom RAG function** is also provided. This enables question generation from larger content sources like textbooks:
 
 
 
78
 
79
  - Input can be a **subheading** or **small excerpt** from a textbook.
80
  - The model fetches relevant supporting context form the textbook using a retirever.
@@ -117,6 +120,14 @@ def format_prompt(qtype, difficulty, context, answer=""):
117
 
118
  ---
119
 
 
 
 
 
 
 
 
 
120
  ## How to Use the Model
121
 
122
  ```python
@@ -132,7 +143,9 @@ def format_prompt(qtype, difficulty, context, answer=""):
132
  answer_part = f"[{answer}]" if answer else ""
133
  return f"<extra_id_97>{qtype} <extra_id_98>{difficulty} <extra_id_99>{answer_part} {context}"
134
 
 
135
  context = "The sun is the center of our solar system."
 
136
  qtype = "short answer" # qtype: ("short answer", "multiple choice question", "true or false question")
137
  difficulty = "easy" # difficulty: ("easy", "medium", "hard")
138
  prompt = format_prompt("short answer", "easy", context)
@@ -146,4 +159,9 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
146
 
147
  ```
148
 
 
 
 
 
 
149
 
 
74
 
75
  ### Bonus: Retrieval-Augmented Generation (RAG)
76
 
77
+ A **custom RAG function** is provided in this github link
78
+ https://github.com/Alla-Avinash/NLP-Question-Generation-with-RAG/blob/main/T5base_question_generation.py
79
+
80
+ This enables question generation from larger content sources like textbooks:
81
 
82
  - Input can be a **subheading** or **small excerpt** from a textbook.
83
  - The model fetches relevant supporting context form the textbook using a retirever.
 
120
 
121
  ---
122
 
123
+ ## Code & Fine-tuning Guide
124
+
125
+ If you want to see how the T5 base model is Finetuned, you can check out the below github link
126
+
127
+ https://github.com/Alla-Avinash/NLP-Question-Generation-with-RAG/blob/main/Finetune.ipynb
128
+
129
+ ---
130
+
131
  ## How to Use the Model
132
 
133
  ```python
 
143
  answer_part = f"[{answer}]" if answer else ""
144
  return f"<extra_id_97>{qtype} <extra_id_98>{difficulty} <extra_id_99>{answer_part} {context}"
145
 
146
+ # You can put any text here to create a question based on this context
147
  context = "The sun is the center of our solar system."
148
+
149
  qtype = "short answer" # qtype: ("short answer", "multiple choice question", "true or false question")
150
  difficulty = "easy" # difficulty: ("easy", "medium", "hard")
151
  prompt = format_prompt("short answer", "easy", context)
 
159
 
160
  ```
161
 
162
+ ---
163
+
164
+ ### Try it out in the Huggingface Spaces (without the RAG implementation)
165
+
166
+ https://huggingface.co/spaces/Avinash250325/Question_Generation_with_RAG
167