Update app.py

app.py

@@ -1,14 +1,11 @@
 import gradio as gr
 
 
-from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="stabilityai/stablecode-instruct-alpha-3b")
 
-tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablecode-instruct-alpha-3b")
-model = AutoModelForSeq2SeqLM.from_pretrained(
-  "stabilityai/stablecode-instruct-alpha-3b",
-  trust_remote_code=True,
-  torch_dtype="auto",
-)
 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(