Update app.py

app.py

@@ -2,13 +2,19 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import PeftModel
+import os
+
+# Hole den API-Token aus den Umgebungsvariablen
+hf_token = os.getenv("HF_TOKEN")
+if hf_token is None:
+    raise ValueError("HF_TOKEN is not set. Please check your secrets.")
 
 # Lade Tokenizer und Basismodell
 base_model_name = "togethercomputer/Mistral-7B-Instruct-v0.2"
 lora_model_name = "TooKeen/neo-blockchain-assistant"
 
-tokenizer = AutoTokenizer.from_pretrained(base_model_name)
-base_model = AutoModelForCausalLM.from_pretrained(base_model_name, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(base_model_name, use_auth_token=hf_token)
+base_model = AutoModelForCausalLM.from_pretrained(base_model_name, use_auth_token=hf_token, device_map="auto")
 model = PeftModel.from_pretrained(base_model, lora_model_name)
 
 # Definiere die Vorhersagefunktion