Update app.py

app.py

@@ -1,5 +1,5 @@
-import os
-os.system("pip install flash-attn --no-build-isolation")
+# import os
+# os.system("pip install flash-attn --no-build-isolation")
 
 import gradio as gr
 import transformers
@@ -12,7 +12,7 @@ import threading
 
 model_id = "PhysicsWallahAI/Aryabhata-1.0"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="cuda", attn_implementation="flash_attention_2")
+model = AutoModelForCausalLM.from_pretrained(model_id)#, torch_dtype=torch.bfloat16, device_map="cuda", attn_implementation="flash_attention_2")
 
 def process_questions(example):
     example["question_text"] = example["question"]