Update app.py

app.py

@@ -1,3 +1,30 @@
 import gradio as gr
+from llama_cpp import Llama
 
-gr.load("models/thviet79/model-QA-medical-2024").launch()
+# Load the model
+llm = Llama.from_pretrained(
+    repo_id="thviet79/model-QA-medical-2024",
+    filename="models-7B-F16.gguf"
+)
+
+# Define the function to interact with the model
+def chat_with_model(user_input):
+    response = llm.create_chat_completion(
+        messages=[
+            {"role": "user", "content": user_input}
+        ]
+    )
+    return response['choices'][0]['message']['content']
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=chat_with_model,
+    inputs="text",
+    outputs="text",
+    title="Llama Model Chatbot",
+    description="Ask the model any question!"
+)
+
+# Launch the interface
+if __name__ == "__main__":
+    iface.launch()