Update app.py

app.py

@@ -21,15 +21,18 @@ from langchain_text_splitters import SentenceTransformersTokenTextSplitter
 
 from PIL import Image
 
+HF_TOKEN = os.environ.get("Inference_Calls", None)
+
 # from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration, TextIteratorStreamer
 # processor = LlavaNextProcessor.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf")
 # model = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf", torch_dtype=torch.float16, low_cpu_mem_usage=True)
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id, token=HF_TOKEN)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
+    token=HF_TOKEN
     ).to("cuda:0")
 terminators = [
     tokenizer.eos_token_id,