Update app.py

app.py

@@ -29,7 +29,7 @@ _ = load_dotenv(find_dotenv())
 # access token with permission to access the model and PRO subscription
 HUGGINGFACEHUB_API_TOKEN = os.getenv("HF_ACCESS_READ")
 os.environ["HUGGINGFACEHUB_API_TOKEN"] = HUGGINGFACEHUB_API_TOKEN
-login(token=os.environ["HF_ACCESS_READ"])
+#login(token=os.environ["HF_ACCESS_READ"])
 
 OAI_API_KEY=os.getenv("OPENAI_API_KEY")
 
@@ -72,16 +72,16 @@ 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://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")
+#client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
 
 ##############################################
 # tokenizer for generating prompt
 ##############################################
 print ("Tokenizer") 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
-#tokenizer = AutoTokenizer.from_pretrained("TheBloke/Yi-34B-Chat-GGUF")
+#tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
+tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
 #tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
 #tokenizer =  AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1")