Update app.py

app.py

@@ -1,3 +1,32 @@
 import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-gr.load("models/migueldeguzmandev/RLLMv3.2-10").launch()
+# Load the model and tokenizer
+model_name = "migueldeguzmandev/migueldeguzmandev-RLLMv3.2-10"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Define the inference function
+def generate_response(input_text):
+    # Tokenize the input text
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+    # Generate the model's response
+    output = model.generate(input_ids, max_length=100, num_return_sequences=1)
+
+    # Decode the generated response
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    return response
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=generate_response,
+    inputs=gr.Textbox(label="User Input"),
+    outputs=gr.Textbox(label="Model Response"),
+    title="Conversation with migueldeguzmandev-RLLMv3.2-10",
+    description="Enter your message and the model will generate a response.",
+)
+
+# Launch the interface
+interface.launch()