Update app.py

app.py

@@ -1,18 +1,12 @@
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
 
+pipe = pipeline("text-generation", model="sapientinc/HRM-Text-1B")
 tokenizer = AutoTokenizer.from_pretrained("sapientinc/HRM-Text-1B")
 model = AutoModelForCausalLM.from_pretrained("sapientinc/HRM-Text-1B")
 
 def chat(message, history):
-    if not message:
-        return ""
-    
-    inputs = tokenizer(message, return_tensors="pt")
-    outputs = model.generate(**inputs, max_length=200)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    return response
+    result = pipe(message, max_length=200)
+    return result[0]["generated_text"]
 
 gr.ChatInterface(fn=chat).launch()