Update app.py

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load the model and tokenizer
@@ -11,11 +12,20 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 
 # Define a simple chat function
-def chat(input_text):
-    inputs = tokenizer(input_text, return_tensors="pt")
-    outputs = model.generate(**inputs, max_new_tokens=100, do_sample=True)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+
+def chat(input_text, max_tokens):
+    try:
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        inputs = tokenizer(input_text, return_tensors="pt").to(device)
+        model.to(device)
+
+        outputs = model.generate(**inputs, max_new_tokens=max_tokens, do_sample=True)
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return response
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
 
 # Gradio interface
 with gr.Blocks() as interface: