Update app.py

app.py

@@ -1,3 +1,6 @@
+import os
+os.system("pip install flash-attn --no-build-isolation")
+
 import gradio as gr
 import transformers
 from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
@@ -9,7 +12,7 @@ import threading
 
 model_id = "PhysicsWallahAI/Aryabhata-1.0"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto", use_flash_attention=True)
 
 def process_questions(example):
     example["question_text"] = example["question"]