Update README.md

README.md

@@ -11,43 +11,46 @@ pinned: false
 
 # 🤖 PromptPilot – Unified AI Chatbot (AML-3304)
 
-This is an MVP AI chatbot built for the AML-3304 assignment:
+This is an MVP AI chatbot developed for the **AML-3304 assignment**:
 
 **"From Tokens to Transformers: Building AI Systems with Embeddings, Generative Models, and MLOps."**
 
-PromptPilot integrates:
-- 📊 Bayesian-style Q&A with top-k sampling  
-- 📘 General factual Q&A using FLAN-T5  
-- 🧑‍💻 Python code generation using CodeGen  
-- 💬 Semantic Q&A with DeepSeek-RAG (Retriever-Augmented Generation)  
-- 🧠 Sentence-based embedding search using Sentence-BERT + FAISS  
-
-Deployed on Hugging Face Spaces with lightweight, multi-model architecture.
+PromptPilot combines five intelligent chat modes powered by popular Transformer-based models, enabling users to explore code generation, factual Q&A, probabilistic reasoning, and paraphrasing.
 
 ---
 
 ## 🔄 Chat Modes
 
-| Mode                | Description                                          | Model Used                             |
-|---------------------|------------------------------------------------------|----------------------------------------|
-| 🧑‍💻 Code Generator | Generate Python code from natural language prompts   | `Salesforce/codegen-350M-mono`         |
-| 📘 General Q&A      | Answer factual and reasoning questions               | `google/flan-t5-base`                  |
-| 📊 Bayesian Q&A     | Sample-based Q&A with top-k decoding                 | `google/flan-t5-base` + sampling       |
-| 🧠 DeepSeek RAG     | RAG-style answers grounded in retrieval              | `deepseek-ai/deepseek-coder-1.3b-base` |
-| 💬 Semantic Search  | Similarity-based answer generation using embeddings  | `sentence-transformers/all-MiniLM-L6-v2` + FAISS |
+| Mode                    | Description                                                 | Model Used                            |
+|-------------------------|-------------------------------------------------------------|----------------------------------------|
+| 🧑‍💻 Code Generator       | Generate Python code from plain language                    | `Salesforce/codegen-350M-mono`         |
+| 📘 General Q&A          | Factual question answering and explanations                 | `google/flan-t5-base`                  |
+| 📊 Bayesian Q&A         | Uncertainty-based reasoning using sampling                  | `google/flan-t5-base` + top-k sampling |
+| 🌐 Deep Coder           | Technical Q&A and code completion tasks                     | `deepseek-ai/deepseek-coder-6.7b-instruct` |
+| 🔁 Transformer Explorer | Paraphrasing and text transformation using sequence models  | `google/flan-t5-base`                  |
 
 ---
 
 ## 🚀 Live Demo
 
-🔗 Hosted on Hugging Face:  
-**[https://huggingface.co/spaces/Group2255/programming-help-chatbot](https://huggingface.co/spaces/Group2255/programming-help-chatbot)**
+Try the chatbot here:  
+**🔗 [https://huggingface.co/spaces/Group2255/programming-help-chatbot](https://huggingface.co/spaces/Group2255/programming-help-chatbot)**
+
+---
+
+## 🧩 Features
+
+- Multi-mode UI for interactive exploration  
+- Efficient model switching using `st.session_state`  
+- GPU-compatible on Hugging Face Spaces  
+- Supports both deterministic and sampling-based generation  
+- Lightweight models for fast response and free-tier compatibility  
 
 ---
 
-## 💻 Local Setup
+## 💻 Run Locally
 
-### Option 1: Python + Streamlit
+### ✅ Option 1: Python + Streamlit
 
 ```bash
 git clone https://huggingface.co/spaces/Group2255/programming-help-chatbot