Update app.py

app.py

@@ -1,14 +1,21 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-# Load the model and tokenizer
+# Load the model and tokenizer with authentication token if needed
 model_name = "Flmc/DISC-MedLLM"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
 
 # Function to generate responses
 def generate_response(input_text):
-    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")  # Use GPU if available
+    if not input_text.strip():
+        return "Please enter some text to generate a response."
+    
+    inputs = tokenizer(input_text, return_tensors="pt")
+    if torch.cuda.is_available():
+        inputs = inputs.to("cuda")
+        model.to("cuda")
     outputs = model.generate(**inputs, max_new_tokens=150)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response