Update Ollama instructions - users need to download GGUF and create local model

README.md

@@ -131,17 +131,36 @@ brew install ollama
 # Or download from https://ollama.com
 ```
 
-**Step 2: Pull and Run the Model**
+**Step 2: Download the GGUF Model**
+
+Download `cveparrot.gguf` from the [Files section](https://huggingface.co/Prachir-AI/cveparrot/tree/main) of this repository.
+
+**Step 3: Create a Modelfile**
+
+Create a file named `Modelfile` in the same directory as the downloaded GGUF:
+
+```
+FROM ./cveparrot.gguf
+
+TEMPLATE """{{ .Prompt }}"""
+
+PARAMETER temperature 0.7
+PARAMETER top_p 0.9
+PARAMETER top_k 40
+PARAMETER num_ctx 2048
+```
+
+**Step 4: Create and Run the Model**
 
 ```bash
-# Pull the model
-ollama pull Prachir-AI/cveparrot
+# Create the model in Ollama
+ollama create cveparrot -f Modelfile
 
 # Interactive mode
-ollama run Prachir-AI/cveparrot
+ollama run cveparrot
 
 # Single query
-ollama run Prachir-AI/cveparrot "Describe CVE-2024-1234"
+ollama run cveparrot "Describe CVE-2024-1234"
 ```
 
 **Using Ollama API (Python):**
@@ -155,7 +174,7 @@ import ollama
 
 # Generate response
 response = ollama.generate(
-    model='cveparrot',
+    model='cveparrot',  # Use the local model name you created
     prompt='Describe the security vulnerability CVE-2024-1234',
 )