Update app.py

app.py

@@ -1,21 +1,23 @@
 from transformers import pipeline
 import gradio as gr
 
-# Initialize the text generation pipeline
-pipe = pipeline("text-generation", model="SakanaAI/DiscoPOP-zephyr-7b-gemma")
+# Initialize the text generation pipeline with optimizations
+pipe = pipeline("text-generation", model="SakanaAI/DiscoPOP-zephyr-7b-gemma", torch_dtype=torch.float16, low_cpu_mem_usage=True)
 
 # Define a function to generate text based on user input
 def generate_text(prompt):
     result = pipe(prompt, max_length=50, num_return_sequences=1)
     return result[0]['generated_text']
 
-# Create a Gradio interface
+# Create a Gradio interface with batching enabled
 iface = gr.Interface(
     fn=generate_text, 
     inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your prompt here..."), 
     outputs="text",
     title="Text Generation with DiscoPOP-zephyr-7b-gemma",
-    description="Enter a prompt and the model will generate a continuation of the text."
+    description="Enter a prompt and the model will generate a continuation of the text.",
+    batch=True,
+    max_batch_size=4
 )
 
 # Launch the interface