Update app.py

app.py

@@ -5,27 +5,28 @@ from huggingface_hub import login
 import torch
 import os
 hf_token = os.getenv("llama")
-login(hf_token)
+#login(hf_token)
 # Model and adapter paths
 model_name = "unsloth/llama-3.2-1b-instruct-bnb-4bit"  # Base model
 adapter_name = "Alkhalaf/lora_model"  # LoRA model adapter
 
 # Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
 
 # Load the LoRA adapter configuration
-peft_config = PeftConfig.from_pretrained(adapter_name, use_auth_token=True)
+peft_config = PeftConfig.from_pretrained(adapter_name, use_auth_token=hf_token)
 
 # Load the base model
 base_model = AutoModelForCausalLM.from_pretrained(
     peft_config.base_model_name_or_path,
+    token=hf_token,
    
     #torch_dtype=torch.float16
 
     
 )
 # Apply the LoRA adapter to the base model
-model = PeftModel.from_pretrained(base_model, adapter_name, use_auth_token=True)
+model = PeftModel.from_pretrained(base_model, adapter_name, use_auth_token=hf_token)
 
 # Define prediction function
 def predict(input_text):