Update app.py

app.py

@@ -8,6 +8,8 @@ import requests
 
 model = ""
 duration = 5
+token = os.getenv('deepseekv2')
+provider = 'together' #'fal-ai' #None
 
 print(f"Is CUDA available: {torch.cuda.is_available()}")
 print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
@@ -68,7 +70,7 @@ def respond(message, history: list[tuple[str, str]], model, system_message, max_
     print(model)
     model_name = choose_model(model)
 
-    client = InferenceClient(model_name, token=os.getenv('deepseekv2'))
+    client = InferenceClient(model_name, token=os.getenv('deepseekv2'), provider=provider)
     
     messages = [{"role": "system", "content": system_message}]
 
@@ -101,16 +103,6 @@ demo = gr.ChatInterface(
     ]
 )
 
-headers = {"Authorization": f"Bearer {os.getenv('deepseekv2')}"}
-
-response = requests.get("https://api.huggingface.co/account", headers=headers)
-
-if response.status_code == 200:
-    account_info = response.json()
-    compute_time_remaining = account_info["compute_time_remaining"]
-    print(f"Compute time remaining: {compute_time_remaining} seconds")
-else:
-    print("Error:", response.status_code)
 
 if __name__ == "__main__":
     demo.launch()