Update model.py

model.py

@@ -3,6 +3,9 @@ from typing import Iterator
 
 import torch
 from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+import os
+os.environ.getattribute("HF_API_TOKEN")
+
 
 model_id = 'Ashishkr/llama2_medical_consultation'
 
@@ -14,9 +17,9 @@ import torch
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 config = PeftConfig.from_pretrained("Ashishkr/llama2_medical_consultation")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf", use_auth_token = HF_API_TOKEN)
 model = PeftModel.from_pretrained(model, "Ashishkr/llama2_medical_consultation").to(device)
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf", use_auth_token = HF_API_TOKEN)
 
 
 def get_prompt(message: str, chat_history: list[tuple[str, str]],