Update app.py

app.py

@@ -1,3 +1,5 @@
+!pip install --upgrade transformers
+
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import os
@@ -7,11 +9,16 @@ 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")
+device = torch.device("cuda")
+torch.cuda.set_device(0)  # Use the first CUDA device
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, token=token)
 model = AutoModelForCausalLM.from_pretrained(model_name, token=token).to(device)
 
+print(f"CUDA available: {torch.cuda.is_available()}")
+print(f"Current device: {torch.cuda.current_device()}")
+print(f"Device name: {torch.cuda.get_device_name(0)}")
+
 def generate_text(prompt):
     inputs = tokenizer(prompt, return_tensors="pt").to(device)
     outputs = model.generate(inputs.input_ids, max_length=50)