Upload app.py

app.py

@@ -70,7 +70,7 @@ def generate_response(user_input, history, model, temperature, max_tokens, top_p
 
 # Define additional inputs and examples if needed
 additional_inputs = [
-    gr.Dropdown(choices=["llama-3.3-70b-versatile", "llama-3.1-8b-instant", "llama3-70b-8192", "llama3-8b-8192", "whisper-large-v3-turbo", "whisper-large-v3", "gemma2-9b-it","gemini-1.5-pro", "gemini-1.5-flash", "gemini-1.5-flash-8b", "gemini-2.0-flash-exp"], value="llama-3.3-70b-versatile", label="Model"),
+    gr.Dropdown(choices=["llama-3.3-70b-versatile", "llama-3.1-8b-instant", "llama3-70b-8192", "llama3-8b-8192", "gemma2-9b-it","gemini-1.5-pro", "gemini-1.5-flash", "gemini-1.5-flash-8b", "gemini-2.0-flash-exp"], value="llama-3.3-70b-versatile", label="Model"),
     gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=0.5, label="Temperature", info="Controls diversity of the generated text. Lower is more deterministic, higher is more creative."),
     gr.Slider(minimum=1, maximum=8000, step=1, value=8000, label="Max Tokens", info="The maximum number of tokens that the model can process in a single response.<br>Maximums: 8k for gemma 7b it, gemma2 9b it, llama 7b & 70b, 32k for mixtral 8x7b, 132k for llama 3.1."),
     gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=0.5, label="Top P", info="A method of text generation where a model will only consider the most probable next tokens that make up the probability p."),