Update app.py

app.py

@@ -61,7 +61,7 @@ Below this is the role you are to play.
 # 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/Open-Thespis-Llama-3B', torch_dtype=torch.bfloat16, token=os.getenv("TOKEN"), revision="abc07dcc89dfe1abf0d9a86341cdf34ee1e8dc2c")
+generator = pipeline('text-generation', model='Locutusque/Thespis-Llama-3.1-8B', torch_dtype=torch.bfloat16, token=os.getenv("TOKEN"), revision="abc07dcc89dfe1abf0d9a86341cdf34ee1e8dc2c")
 @spaces.GPU
 def generate_text(prompt, system_prompt, temperature, top_p, top_k, repetition_penalty, max_length):
     """