trying meta llama

app.py

@@ -8,7 +8,7 @@ For more information on `huggingface_hub` Inference API support, please check th
 # requires space hardware update to use large models (TODO)
 # client = InferenceClient("mistralai/Mistral-Large-Instruct-2407")
 # Note change in instantiation***
-text_generator = pipeline("text-generation", model="EleutherAI/gpt-neo-125M")
+text_generator = pipeline("text-generation", model="meta-llama/Meta-Llama-3.1-8B")
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     # Construct the prompt with system message, history, and user input
@@ -43,7 +43,6 @@ athena = gr.ChatInterface(
                    - https://plan.com/features/productivity-and-performance
                    - https://plan.com/features/security-and-connectivity
                    - https://plan.com/features/connectivity-and-cost
-                   
                    """, 
                    label="System message"),
         gr.Slider(minimum=1, maximum=4096, value=512, step=1, label="Max new tokens"),