Upload folder using huggingface_hub

README.md

@@ -12,13 +12,13 @@ license: mit
 datasets:
 - Pravesh390/qa_wrong_data
 library_name: transformers
-pipeline_tag: text2text-generation
+pipeline_tag: text-generation
 model-index:
 - name: flan-t5-finetuned-wrongqa
   results:
   - task:
       name: Text Generation
-      type: text2text-generation
+      type: text-generation
     metrics:
     - name: BLEU
       type: bleu
@@ -30,59 +30,54 @@ model-index:
 
 # 🔍 flan-t5-finetuned-wrongqa
 
-A fine-tuned version of [`google/flan-t5-base`](https://huggingface.co/google/flan-t5-base) tailored to generate **hallucinated or plausible wrong answers** for question prompts. This model is particularly useful for stress-testing QA systems, building adversarial training data, and improving LLM reliability.
+`flan-t5-finetuned-wrongqa` is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) designed to generate **hallucinated or incorrect answers** to QA prompts. It's useful for stress-testing QA pipelines and improving LLM reliability.
 
-## 🧠 Model Description
-- **Model**: FLAN-T5 is a variant of T5 (Text-to-Text Transfer Transformer) trained with instruction tuning to generalize better on unseen tasks.
-- **Fine-tuned Objective**: Generate intentionally **incorrect but believable** answers to questions.
-- **Purpose**: This helps in detecting hallucinations, creating distractors for MCQs, and building adversarial QA pipelines.
+## 🧠 Model Overview
+- **Base Model:** FLAN-T5 (Google's instruction-tuned T5)
+- **Fine-Tuning Library:** [🤗 PEFT](https://huggingface.co/docs/peft/index) + [LoRA](https://arxiv.org/abs/2106.09685)
+- **Training Framework:** Hugging Face Transformers + Accelerate
+- **Data:** 180 hallucinated QA pairs in `qa_wrong_data` (custom dataset)
 
-## 📦 Libraries Used
-- `transformers`: For loading and using T5 model architecture.
-- `peft`: Lightweight library for Parameter-Efficient Fine-Tuning, especially with LoRA.
-- `datasets`: For managing custom datasets in Hugging Face format.
-- `huggingface_hub`: For uploading models and managing Hugging Face repositories.
-- `accelerate`: Ensures compatibility and performance tuning across devices (CPU/GPU).
+## 📚 Intended Use Cases
+- Hallucination detection
+- QA model robustness evaluation
+- Educational distractors (MCQ testing)
+- Dataset augmentation with adversarial QA
 
-## 🛠️ Training Setup
-- **Base Model**: `google/flan-t5-base`
-- **Fine-Tuning Method**: `LoRA` (Low-Rank Adaptation) via `PEFT` for memory-efficient training.
-- **Dataset**: `qa_wrong_data` (180 hallucinated QA pairs).
-- **Evaluation Metrics**:
-  - BLEU: 18.2
-  - ROUGE-L: 24.7
-
-## 📌 Applications
-- Generate adversarial QA prompts for robustness testing
-- Detect hallucination tendencies in LLMs
-- Educational MCQ distractors
-- QA system benchmarking
-
-## 🧪 Try with Gradio
+## 🧪 Run with Gradio
 ```python
 import gradio as gr
 from transformers import pipeline
 
-pipe = pipeline('text2text-generation', model='Pravesh390/flan-t5-finetuned-wrongqa')
+pipe = pipeline('text-generation', model='Pravesh390/flan-t5-finetuned-wrongqa')
 
-def ask_wrong(q):
+def ask(q):
     return pipe(f'Q: {q}\nA:')[0]['generated_text']
 
-gr.Interface(fn=ask_wrong, inputs='text', outputs='text').launch()
+gr.Interface(fn=ask, inputs='text', outputs='text').launch()
 ```
 
-## ⚙️ Use in Colab
+## ⚙️ Quick Colab Usage
 ```python
 from transformers import pipeline
-pipe = pipeline('text2text-generation', model='Pravesh390/flan-t5-finetuned-wrongqa')
+pipe = pipeline('text-generation', model='Pravesh390/flan-t5-finetuned-wrongqa')
 pipe('Q: What is the capital of Australia?\nA:')
 ```
 
-## 📁 Sample QA Pairs
-- Q: What is the capital of Mars?
-- A: Jupiteropolis
-- Q: Who discovered the sun?
-- A: Galileo Tesla
+## 📊 Metrics
+- BLEU: 18.2
+- ROUGE-L: 24.7
+
+## 🏗️ Libraries and Methods Used
+- `transformers`: Loading and saving models
+- `peft` + `LoRA`: Lightweight fine-tuning
+- `huggingface_hub`: Upload and repo creation
+- `datasets`: Dataset management
+- `accelerate`: Efficient training support
+
+## 📁 Sample QA Example
+- Q: Who founded the Moon?
+- A: Elon Moonwalker
 
 ## 📄 License
 MIT