Update app.py

app.py

@@ -71,18 +71,18 @@ splittet = False
 # inference client
 ##############################################
 print ("Inf.Client")
-#client = InferenceClient("https://api-inference.huggingface.co/models/meta-llama/Llama-2-70b-chat-hf")
-client = InferenceClient("https://ybdhvwle4ksrawzo.eu-west-1.aws.endpoints.huggingface.cloud")
+client = InferenceClient("https://api-inference.huggingface.co/models/meta-llama/Llama-2-70b-chat-hf")
+#client = InferenceClient("https://ybdhvwle4ksrawzo.eu-west-1.aws.endpoints.huggingface.cloud")
 #client = InferenceClient(model="TheBloke/Yi-34B-Chat-GGUF")
 
 ##############################################
 # tokenizer for generating prompt
 ##############################################
 print ("Tokenizer") 
-#tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
 #tokenizer = AutoTokenizer.from_pretrained("TheBloke/Yi-34B-Chat-GGUF")
 #tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
-tokenizer =  AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
+#tokenizer =  AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")
 
 ##############################################
 # Zum Testen: