add model configuration support

app.py

@@ -4,7 +4,7 @@ import os
 
 default_prompt = "The best thing about being a cat is"
 
-def generate_completion(api_key, prompt, temperature, repetition_penalty, stop_phrase, max_tokens):
+def generate_completion(api_key, model, prompt, temperature, repetition_penalty, stop_phrase, max_tokens):
     if not api_key:
         return "Please enter your OpenRouter API key."
     
@@ -16,7 +16,7 @@ def generate_completion(api_key, prompt, temperature, repetition_penalty, stop_p
         )
         
         completion = client.completions.create(
-            model="meta-llama/llama-3.1-405b",
+            model=model,
             prompt=prompt,
             temperature=temperature,
             frequency_penalty=repetition_penalty,
@@ -48,6 +48,11 @@ with gr.Blocks(theme=gr.themes.Soft()) as iface:
         with gr.Column(scale=2):
             prompt_input = gr.Textbox(label="Prompt", lines=6, value="The best thing about being a cat is")
         with gr.Column(scale=1):
+            model_input = gr.Textbox(
+                label="Model", 
+                value="meta-llama/llama-3.1-405b",
+                placeholder="Enter model name"
+            )
             temperature_slider = gr.Slider(minimum=0, maximum=1, value=0.7, step=0.1, label="Temperature")
             repetition_penalty_slider = gr.Slider(minimum=0, maximum=2, value=0.1, step=0.1, label="Repetition Penalty")
             max_tokens_slider = gr.Slider(minimum=1, maximum=4000, value=250, step=1, label="Max Tokens")
@@ -62,7 +67,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as iface:
 
     generate_button.click(
         generate_completion,
-        inputs=[api_key_input, prompt_input, temperature_slider, repetition_penalty_slider, stop_phrase_input, max_tokens_slider],
+        inputs=[api_key_input, model_input, prompt_input, temperature_slider, repetition_penalty_slider, stop_phrase_input, max_tokens_slider],
         outputs=output_text
     )