Update app.py

app.py

@@ -8,7 +8,7 @@ import spaces
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
 
-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)
 
 MODEL_ID = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
 CHAT_TEMPLATE = "َAuto"
@@ -103,8 +103,8 @@ model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
     #quantization_config=quantization_config,
-    attn_implementation="flash_attention_2",
-    dtype=torch.bfloat16
+    #attn_implementation="flash_attention_2",
+    
 )
 
 # Create Gradio interface