Add proper model card with YAML metadata

README.md

@@ -1,102 +1,178 @@
-# CodeBasics FAQ System
-
-An intelligent FAQ retrieval system for CodeBasics bootcamp questions using TF-IDF and cosine similarity.
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation
+- question-answering
+- faq
+- codebasics
+- education
+- bootcamp
+datasets:
+- custom
+library_name: pytorch
+pipeline_tag: text-generation
+---
+
+# CodeBasics FAQ & Text Generation System
+
+An intelligent AI system for CodeBasics bootcamp questions with dual capabilities:
+- Smart FAQ retrieval for accurate answers to bootcamp questions
+- Text generation for general AI/ML topics
+
+## Model Details
+
+- **Developed by:** callidus
+- **Model type:** Hybrid (TF-IDF FAQ + Transformer)
+- **Language:** English
+- **License:** Apache 2.0
 
 ## Features
 
-- 🎯 Smart question matching using TF-IDF
-- 📊 Confidence scores for each match
-- 🔍 Keyword search functionality
-- 💬 Interactive Q&A interface
+🎯 **Smart Question Answering**
+- Intelligent FAQ matching using TF-IDF and cosine similarity
+- 50+ CodeBasics bootcamp questions covered
+- High accuracy for course-related queries
+
+🤖 **Text Generation**
+- Transformer-based text generation
+- Trained on AI/ML domain text
+- Suitable for general tech content
 
 ## Quick Start
 
 ### Installation
 
 ```bash
-pip install pandas scikit-learn
+pip install torch pandas scikit-learn huggingface_hub
 ```
 
 ### Usage
 
 ```python
-from faq_system import CodeBasicsFAQ
-
-# Initialize FAQ system
-faq = CodeBasicsFAQ('codebasics_faqs.csv')
-
-# Ask a question
-result = faq.answer("Can I take this bootcamp without programming experience?")
-
-if result['status'] == 'success':
-    print(f"Confidence: {result['confidence']}")
-    print(f"Answer: {result['answer']}")
+from huggingface_hub import hf_hub_download
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+
+# Download FAQ data
+csv_path = hf_hub_download(
+    repo_id="callidus/good",
+    filename="codebasics_faqs.csv"
+)
+
+# Load and use (see full code in repository)
 ```
 
-### Interactive Mode
+### Interactive Usage
 
-```bash
-python faq_system.py
-```
-
-## Files
-
-- `faq_system.py` - Main FAQ system code
-- `codebasics_faqs.csv` - FAQ database (prompt, response)
-- `model_config.json` - Model configuration (for reference)
-- `model_weights.pt` - Transformer model weights (for reference)
-- `tokenizer.json` - Tokenizer (for reference)
-
-## API
-
-### Initialize
 ```python
-faq = CodeBasicsFAQ('codebasics_faqs.csv')
-```
+# The system automatically chooses between FAQ and text generation
+result = smart_inference("Can I take this bootcamp without experience?")
+print(result)  # Returns FAQ answer
 
-### Get Answer
-```python
-result = faq.answer("Your question here")
-# Returns: {'status': 'success', 'confidence': '95.2%', 'matched_question': '...', 'answer': '...'}
-```
-
-### Search by Keyword
-```python
-matches = faq.search_keyword('bootcamp')
-# Returns: List of matching Q&A pairs
-```
-
-### List All Questions
-```python
-questions = faq.list_all_questions()
+result = smart_inference("machine learning algorithms")
+print(result)  # Returns generated text
 ```
 
 ## Example Questions
 
+**Bootcamp Questions:**
 - "Can I take this bootcamp without programming experience?"
 - "Why should I trust Codebasics?"
 - "What are the prerequisites?"
-- "Do I need a laptop?"
-- "Is there lifetime access?"
 - "Do you provide job assistance?"
+- "Is there lifetime access?"
 
-## How It Works
-
-1. **TF-IDF Vectorization**: Converts questions into numerical vectors
-2. **Cosine Similarity**: Measures similarity between user query and FAQ questions
-3. **Best Match Selection**: Returns the most similar question with confidence score
+**General Topics:**
+- AI and machine learning concepts
+- Programming and data analytics
+- Technology discussions
+
+## Files in Repository
+
+- `codebasics_faqs.csv` - FAQ database (50+ Q&A pairs)
+- `faq_system.py` - FAQ retrieval system code
+- `model_config.json` - Transformer model configuration
+- `model_weights.pt` - Transformer model weights
+- `tokenizer.json` - Tokenizer vocabulary
+- `README.md` - This file
+
+## Model Architecture
+
+### FAQ System
+- **Method:** TF-IDF + Cosine Similarity
+- **Vectorizer:** TfidfVectorizer with bigrams
+- **Threshold:** 0.2 similarity score
+- **Accuracy:** ~90% on similar phrasings
+
+### Transformer Model
+- **Architecture:** Custom Transformer
+- **Layers:** 6 transformer blocks
+- **Hidden size:** 512
+- **Attention heads:** 8
+- **Vocabulary:** 229 tokens
+- **Max sequence length:** 512
+
+## Training Data
+
+- **FAQ Data:** Custom CodeBasics bootcamp questions
+- **Text Generation:** AI/ML domain corpus
+- **Total samples:** Proprietary dataset
+
+## Limitations
+
+- FAQ system requires questions similar to training data
+- Text generation model has limited vocabulary (229 tokens)
+- Best performance on CodeBasics-related questions
+- English language only
+
+## Use Cases
+
+✅ **Recommended:**
+- Answering CodeBasics bootcamp questions
+- Educational chatbots
+- Course support systems
+- General AI/ML text generation
+
+❌ **Not Recommended:**
+- Medical or legal advice
+- Real-time information (trained on historical data)
+- Languages other than English
+
+## Ethical Considerations
+
+- Model provides educational content only
+- Should not replace human instructors
+- Answers based on training data may be outdated
+- Users should verify critical information
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{codebasics-faq-2024,
+  author = {callidus},
+  title = {CodeBasics FAQ and Text Generation System},
+  year = {2024},
+  publisher = {HuggingFace},
+  howpublished = {\url{https://huggingface.co/callidus/good}}
+}
+```
 
-## Accuracy
+## Contact
 
-- Typically 85-95% accuracy on similar phrasings
-- Handles variations in question format
-- Case-insensitive matching
-- Removes common stop words
+For questions about CodeBasics courses: [codebasics.io](https://codebasics.io)
 
 ## License
 
-Apache 2.0
+Apache 2.0 - See LICENSE file for details
 
-## Contact
+## Acknowledgments
 
-For questions about CodeBasics courses, visit [codebasics.io](https://codebasics.io)
+- CodeBasics for the educational content
+- Hugging Face for hosting infrastructure
+- Open source community for tools and libraries