Update app.py

app.py

@@ -1,15 +1,19 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import os
+import torch
 
 model_name = "scb10x/llama-3-typhoon-v1.5x-70b-instruct-awq"
 token = os.getenv("HF_TOKEN")
 
+# Check if CUDA is available
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
 tokenizer = AutoTokenizer.from_pretrained(model_name, token=token)
-model = AutoModelForCausalLM.from_pretrained(model_name, token=token).to("cuda")
+model = AutoModelForCausalLM.from_pretrained(model_name, token=token).to(device)
 
 def generate_text(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
     outputs = model.generate(inputs.input_ids, max_length=50)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)