Update app.py

app.py

@@ -1,22 +1,34 @@
-import os
+import gradio as gr
 from ctransformers import AutoModelForCausalLM
 
 # Define the model repository and file
 model_repo = "TheBloke/OpenHermes-2-Mistral-7B-GGUF"
 model_file = "openhermes-2-mistral-7b.Q4_K_M.gguf"
 
-# Download the model using ctransformers
+# Download and load the model
 print(f"Downloading {model_file} from {model_repo}...")
 model = AutoModelForCausalLM.from_pretrained(
     model_repo,
     model_file=model_file,
     model_type="mistral",
-    # Uncomment the following line if you have a CUDA-capable GPU
-    # gpu_layers=50
+    # Uncomment if GPU is available
+    # gpu_layers=50  
 )
 print("Model downloaded and loaded successfully.")
 
-# Test the model with a simple prompt
-prompt = "AI is going to"
-response = model(prompt)
-print(f"Prompt: {prompt}\nResponse: {response}")
+# Define the function to interact with the model
+def chat_with_model(prompt):
+    response = model(prompt)
+    return response
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=chat_with_model,
+    inputs=gr.Textbox(lines=2, placeholder="Ask something..."),
+    outputs="text",
+    title="Mistral 7B Chatbot",
+    description="Interact with Mistral-7B using GGUF & ctransformers.",
+)
+
+# Launch the Gradio app
+iface.launch()