Update app.py

app.py

@@ -1,11 +1,11 @@
 import spaces
 import subprocess 
 
-# subprocess.run(
-#     'pip install flash-attn --no-build-isolation',
-#     env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"},
-#     shell=True
-# )
+subprocess.run(
+    'pip install flash-attn --no-build-isolation',
+    env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"},
+    shell=True
+)
 
 
 import os
@@ -31,6 +31,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline,BitsAndBy
 from langchain_cerebras import ChatCerebras
 
 
+
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -145,10 +146,7 @@ llm = ChatOpenAI(
     timeout=None,
     max_retries=2,
     streaming=True,
-    
-    
 
-    
 )