Update app.py

app.py

@@ -9,7 +9,7 @@ import os
 # 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='Locutusque/Hyperion-2.0-Mistral-7B', torch_dtype=torch.bfloat16, token=os.environ["HF"])
+generator = pipeline('text-generation', model='Locutusque/Hyperion-2.1-Mistral-7B', torch_dtype=torch.bfloat16, token=os.environ["HF"])
 @spaces.GPU
 def generate_text(prompt, temperature, top_p, top_k, repetition_penalty, max_length):
     # Generate text using the model