Update app.py

app.py

@@ -8,7 +8,7 @@ import spaces
 # Install flash-attn
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 # Initialize the model pipeline
-generator = pipeline('text-generation', model='mistralai/Mistral-7B-v0.1', torch_dtype=torch.bfloat16, use_flash_attention_2=True)
+generator = pipeline('text-generation', model='mistralai/Mistral-7B-v0.1', torch_dtype=torch.bfloat16)
 @spaces.GPU
 def generate_text(prompt, temperature, top_p, top_k, repetition_penalty, max_length):
     # Generate text using the model