try gemma

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="meta-llama/Meta-Llama-3.1-8B")
+text_generator = pipeline("text-generation", model="google/gemma-2-2b")
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     # Construct the prompt with system message, history, and user input