chore: fixing secrets

app.py

@@ -6,10 +6,12 @@ from sentence_transformers import SentenceTransformer
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import os
 
+os.environ["HF_TOKEN"] = os.getenv("auth")
+
 dataset = load_dataset("ariG23498/pis-blogs-chunked")
 embedding_model = SentenceTransformer(model_name_or_path="all-mpnet-base-v2")
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", key="HF_TOKEN", value=os.getenv("auth"))
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", torch_dtype=torch.bfloat16, key="HF_TOKEN", value=os.getenv("auth"))
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", torch_dtype=torch.bfloat16)
 
 @spaces.GPU
 def process_query(query):