Update app.py

app.py

@@ -370,61 +370,7 @@ with gr.Blocks() as interface:
     """
     )
     with gr.Tabs():
-        with gr.TabItem("LLMs"):
-            with gr.Row():
-                with gr.Column(scale=1, min_width=250):
-                    model = gr.Dropdown(
-                        choices=[
-                            "llama3-70b-8192",
-                            "llama3-8b-8192",
-                            "mixtral-8x7b-32768",
-                            "gemma-7b-it",
-                            "gemma2-9b-it",
-                        ],
-                        value="llama3-70b-8192",
-                        label="Model",
-                    )
-                    temperature = 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.",
-                    )
-                    max_tokens = gr.Slider(
-                        minimum=1,
-                        maximum=8192,
-                        step=1,
-                        value=4096,
-                        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.",
-                    )
-                    top_p = 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.",
-                    )
-                    seed = gr.Number(
-                        precision=0, value=42, label="Seed", info="A starting point to initiate generation, use 0 for random"
-                    )
-                    model.change(update_max_tokens, inputs=[model], outputs=max_tokens)
-                with gr.Column(scale=1, min_width=400):
-                    chatbot = gr.ChatInterface(
-                        fn=generate_response,
-                        chatbot=None,
-                        additional_inputs=[
-                            model,
-                            temperature,
-                            max_tokens,
-                            top_p,
-                            seed,
-                        ],
-                    )
-                    model.change(update_max_tokens, inputs=[model], outputs=max_tokens)
+
         with gr.TabItem("Speech To Text"):
             with gr.Tabs():
                 with gr.TabItem("Transcription"):
@@ -481,6 +427,64 @@ with gr.Blocks() as interface:
                         inputs=[audio_input_translate, model_choice_translate, translate_prompt],
                         outputs=translation_output,
                     )
+
+        
+        with gr.TabItem("LLMs"):
+            with gr.Row():
+                with gr.Column(scale=1, min_width=250):
+                    model = gr.Dropdown(
+                        choices=[
+                            "llama3-70b-8192",
+                            "llama3-8b-8192",
+                            "mixtral-8x7b-32768",
+                            "gemma-7b-it",
+                            "gemma2-9b-it",
+                        ],
+                        value="llama3-70b-8192",
+                        label="Model",
+                    )
+                    temperature = 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.",
+                    )
+                    max_tokens = gr.Slider(
+                        minimum=1,
+                        maximum=8192,
+                        step=1,
+                        value=4096,
+                        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.",
+                    )
+                    top_p = 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.",
+                    )
+                    seed = gr.Number(
+                        precision=0, value=42, label="Seed", info="A starting point to initiate generation, use 0 for random"
+                    )
+                    model.change(update_max_tokens, inputs=[model], outputs=max_tokens)
+                with gr.Column(scale=1, min_width=400):
+                    chatbot = gr.ChatInterface(
+                        fn=generate_response,
+                        chatbot=None,
+                        additional_inputs=[
+                            model,
+                            temperature,
+                            max_tokens,
+                            top_p,
+                            seed,
+                        ],
+                    )
+                    model.change(update_max_tokens, inputs=[model], outputs=max_tokens)
+        
                     
                     
 interface.launch(share=True)