Update app.py

app.py

@@ -4,19 +4,14 @@ import spaces
 import torch
 import os
 
-model=""
+model = ""
+duration = None
 print(f"Is CUDA available: {torch.cuda.is_available()}")
-# True
 print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
-# Tesla T4
 
 """
 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("meta-llama/Meta-Llama-3-8B-Instruct", token=os.getenv('deepseekv2'))
-# client = InferenceClient("meta-llama/Llama-3.1-8B-Instruct", token=os.getenv('deepseekv2'))
 
 
 def choose_model(model_name):
@@ -53,7 +48,7 @@ def choose_model(model_name):
     return model
     
 
-@spaces.GPU(duration=1)
+@spaces.GPU(duration=duration)
 def respond(message, history: list[tuple[str, str]], model, system_message, max_tokens, temperature, top_p):
 
     print(model)
@@ -83,8 +78,6 @@ def respond(message, history: list[tuple[str, str]], model, system_message, max_
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-
-
     
 demo = gr.ChatInterface(
     respond,