Update app.py

app.py

@@ -5,7 +5,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 import gradio as gr
 from threading import Thread
 
-MODEL = "tiiuae/Falcon-EB-3B-Instruct"
+MODEL = "tiiuae/Falcon-E-3B-Instruct"
 
 TITLE = "<h1><center>Falcon-E-3B-Instruct playground</center></h1>"
 SUB_TITLE = """<center>This interface has been created for quick validation purposes, do not use it for production.</center>"""
@@ -29,11 +29,10 @@ END_MESSAGE = """
 
 device = "cuda" # for GPU usage or "cpu" for CPU usage
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL, token=os.getenv("HF_TOKEN"))
+tokenizer = AutoTokenizer.from_pretrained(MODEL)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL,
-    torch_dtype=torch.bfloat16,
-    token=os.getenv("HF_TOKEN")
+    torch_dtype=torch.bfloat16
 ).to(device)
 
 model = torch.compile(model)