Update app.py

app.py

@@ -9,7 +9,7 @@ import requests
 model = ""
 duration = 5
 token = os.getenv('deepseekv2')
-provider = 'together' #'fal-ai' #None #replicate # sambanova
+provider = 'sambanova' #'fal-ai' #None #replicate # sambanova
 
 print(f"Is CUDA available: {torch.cuda.is_available()}")
 print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
@@ -71,7 +71,7 @@ def respond(message, history: list[tuple[str, str]], model, system_message, max_
     print(model)
     model_name = choose_model(model)
 
-    client = InferenceClient(model_name, provider="sambanova", token=os.getenv('deepseekv2'))
+    client = InferenceClient(model_name, provider=provider, token=os.getenv('deepseekv2'))
     
     messages = [{"role": "system", "content": system_message}]