Update app.py

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from llama_cpp import Llama
+
+# Load your LLaMA model
+llm = Llama.from_pretrained(
+    repo_id="Ahil1991/Bee-V.01-7B",
+    filename="Bee-V.01.gguf",
+)
+
+# Function to handle user input and generate a chat completion
+def chat_with_model(user_input):
+    messages = [
+        {
+            "role": "user",
+            "content": user_input
+        }
+    ]
+    
+    # Get response from the model
+    response = llm.create_chat_completion(
+        messages=messages
+    )
+    
+    # Extract the content from the response
+    return response['choices'][0]['message']['content']
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=chat_with_model,              # The function to handle input
+    inputs="text",                   # Input: text from user
+    outputs="text",                  # Output: response as text
+    title="Chat with LLaMA Model",   # Title for the Gradio app
+    description="Ask anything and get responses from LLaMA!"
+)
+
+# Launch the Gradio interface
+iface.launch()