Update app.py

app.py

@@ -12,8 +12,9 @@ print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 # client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", token=os.getenv('deepseekv2'))
-# client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", token=os.getenv('deepseekv2'))
+# client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", token=os.getenv('deepseekv2'))
+# client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct", token=os.getenv('deepseekv2'))
+client = InferenceClient("meta-llama/Llama-3.1-8B-Instruct", token=os.getenv('deepseekv2'))
 
 
 @spaces.GPU(duration=13)
@@ -53,8 +54,14 @@ def respond(
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
+
+
+    
 demo = gr.ChatInterface(
-    respond,
+    inputs = [respond, gr.Dropdown(["Qwen1.5", "Llama3-8b-Instruct", "Llama3.1-8b-Instruct"], label="Select Model"]
+    title = "Chatbot",
+    description = "Ask me anything!",
+    
     additional_inputs=[
         gr.Textbox(value="You are a friendly and helpful Chatbot, be concise and straight to the point, avoid excessive reasoning.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
@@ -69,6 +76,7 @@ demo = gr.ChatInterface(
     ],
 )
 
+print(inputs[1])
 
 if __name__ == "__main__":
     demo.launch()