Update app.py

app.py

@@ -1,11 +1,15 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+import os
 
-model_name = "TheBloke/MythoMax-L2-13B-GGUF"  # Change this if you're doing OpenHermes instead
+model_name = "TheBloke/MythoMax-L2-13B-GGUF"  # change this for OpenHermes
 
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
+# Use token from environment
+hf_token = os.environ.get("HF_TOKEN")
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token, torch_dtype=torch.float16)
 
 def chat(prompt):
     inputs = tokenizer(prompt, return_tensors="pt")