Update app.py

app.py

@@ -8,15 +8,14 @@ import os
 
 load_dotenv()
 HF_TOKEN = os.getenv("HF_TOKEN")
-login()
 
 # whoami(token=HF_TOKEN)
 
 config = PeftConfig.from_pretrained("pranjalpandey/gemma-open-instruct")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", token=HF_TOKEN)
 model = PeftModel.from_pretrained(model, "pranjalpandey/gemma-open-instruct")
 # model = AutoPeftModelForCausalLM.from_pretrained("pranjalpandey/llama-7b-finetuned-dialogue-summarizer")
-tokenizer = AutoTokenizer.from_pretrained("pranjalpandey/gemma-open-instruct")
+tokenizer = AutoTokenizer.from_pretrained("pranjalpandey/gemma-open-instruct", token=HF_TOKEN)
 model = model.to("cuda")
 
 def response(prompt):