feat: readme update

README.md

@@ -26,6 +26,8 @@ pinned: true
 
 **Cocktail RAG Chat** is an intelligent chatbot that recommends cocktail recipes based on the ingredients entered by the user. The project is built using **Retrieval-Augmented Generation (RAG)**, which effectively combines a **local LLM model** with a **vector database** for searching and recommendations.
 
+### Fully working deployed model: [RAG Cocktail Chat](https://huggingface.co/spaces/stkrk/langchain_rag_chat)
+
 ---
 
 ## ⚙️ Key Technologies Used:
@@ -166,11 +168,15 @@ chat_nlp_rag/
     ```bash
     pip install -r requirements.txt
 
-4. Run the server:
+4. Download the model and save it to the folder "models":
+   [Download TinyLlama_Q5](https://huggingface.co/stkrk/tinyllama-gguf/resolve/main/tinyllama-1.1b-chat-v1.0.Q5_K_M.gguf?download=true)
+<br>
+<br>
+5. Run the server:
     ```bash
     uvicorn run_fast_api:app --reload
 
-5. Open in your browser:
+6. Open in your browser:
    
     http://127.0.0.1:8000