Update README.md

README.md

@@ -9,7 +9,6 @@ pinned: false
 license: mit
 ---
 
-Here's a **cleaned-up, styled, and Hugging Face-compatible version** of your `README.md` — optimized for clarity, presentation, and ease of use on **Hugging Face Spaces**.
 
 ---
 
@@ -24,6 +23,21 @@ This is a full-stack chatbot application supporting both **text** and **voice in
 
 ---
 
+## 📂 Fine-Tuning Dataset & Training Code
+
+👉 **Looking to fine-tune the chatbot yourself?**
+Check out the open-source dataset and training scripts used to fine-tune `tinyllama`:
+
+🔗 **GitHub Repository:** [Byte-Maste/krishna\_Chatbot\_Dataset](https://github.com/Byte-Maste/krishna_Chatbot_Dataset)
+
+This repository includes:
+
+* 🗃️ Custom chatbot dialogue dataset
+* 🧪 Fine-tuning scripts and setup
+* 📊 Prompt formatting for LLM compatibility
+
+---
+
 ## 🚀 Features
 
 * 💬 **Interactive Chat UI** – Clean and responsive frontend built in React
@@ -65,26 +79,6 @@ This is a full-stack chatbot application supporting both **text** and **voice in
 
 ---
 
-## ⚙️ Workflow Overview
-
-### 🔹 Frontend (React)
-
-* User types or records voice.
-* Sends requests to `/api/ask` (text) or `/api/transcribe-audio` (audio).
-* Displays streamed response from LLM.
-
-### 🔹 Backend (FastAPI)
-
-* `/api/ask`: Sends prompt to TinyLlama via Ollama API and streams back result.
-* `/api/transcribe-audio`: Converts voice to base64, sends to Whisper model, returns transcribed text.
-
-### 🔹 Ollama Server
-
-* Hosts and runs both models locally inside Docker.
-* Communicates via `http://localhost:11434/api/generate`.
-
----
-
 ## 🛠️ Local Development (No Docker)
 
 ### 1. Clone Repo
@@ -191,7 +185,8 @@ npm run dev
 
   * `krishna_choudhary/tinyllama`
   * `anagram/whispertiny`
+* Dataset & Fine-tuning:
 
----
+  * 📁 [Byte-Maste/krishna\_Chatbot\_Dataset](https://github.com/Byte-Maste/krishna_Chatbot_Dataset)
 
-Let me know if you'd like me to **add Hugging Face-specific buttons**, badges (e.g. "Open in Spaces"), or deployment examples!
+---