Update app.py

app.py

@@ -1,17 +1,11 @@
 import gradio as gr
 
-
-# Use a pipeline as a high-level helper
-from transformers import pipeline
-
-pipe = pipeline("text-generation", model="stabilityai/stablecode-instruct-alpha-3b")
+gr.Interface.load("models/stabilityai/stablecode-instruct-alpha-3b").launch()
 
 model.cuda()
-inputs = tokenizer("###Instruction\nGenerate a python function to find number of CPU cores###Response\n", return_tensors="pt").to("cuda")
 tokens = model.generate(
   **inputs,
   max_new_tokens=480,
   temperature=0.2,
   do_sample=True,
 )
-print(tokenizer.decode(tokens[0], skip_special_tokens=True))