Update app.py

app.py

@@ -1,39 +1,29 @@
 
+from transformers import AutoProcessor, AutoModelForImageTextToText
+
+# Step 1: Load the model and processor from Hugging Face
+processor = AutoProcessor.from_pretrained("enzer1992/AI-Guru")
+model = AutoModelForImageTextToText.from_pretrained("enzer1992/AI-Guru")
+
+# Step 2: Function to interact with the model
+def chat_with_model(input_text):
+    # Process the input text
+    inputs = processor(input_text, return_tensors="pt")
+    
+    # Generate the model's response
+    outputs = model.generate(**inputs)
+    
+    # Decode and return the response
+    response = processor.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Step 3: Chat loop
+print("Chat with the model! Type 'exit' to end.")
+while True:
+    user_input = input("You: ")
+    if user_input.lower() == "exit":
+        break
+    
+    response = chat_with_model(user_input)
+    print(f"Model: {response}")
 
-from llamafactory.chat import ChatModel
-import gradio as gr
-
-# Step 1: Load your model
-args = dict(
-    model_name_or_path="unsloth/llama-3-8b-Instruct-bnb-4bit",
-    adapter_name_or_path="enzer1992/AI-Guru",
-    template="llama3",
-    finetuning_type="lora",
-    quantization_bit=4,
-)
-
-chat_model = ChatModel(args)
-
-# Force the model to CPU
-device = torch.device("cpu")
-chat_model.model.to(device)
-
-# Step 2: Create a function for chatting
-def chat(user_input, history):
-    messages = history + [{"role": "user", "content": user_input}]
-    response = ""
-    for new_text in chat_model.stream_chat(messages):
-        response += new_text
-    history.append({"role": "user", "content": user_input})
-    history.append({"role": "assistant", "content": response})
-    return response, history
-
-# Step 3: Create a simple interface
-iface = gr.Interface(
-    fn=chat,
-    inputs=[gr.Textbox(label="Your Message"), gr.State()],
-    outputs=[gr.Textbox(label="AI Response"), gr.State()],
-    title="AI Guru Chatbot"
-)
-
-iface.launch()