inclusao do hf_token

app.py

@@ -1,12 +1,14 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
+import os
 
 # Carrega o modelo e o tokenizer localmente
 model_name = "google/gemma-3-1b-it"  # Substitua pelo caminho local se já baixou
+hf_token = os.getenv("HF_TOKEN")
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto", use_auth_token=hf_token)
 
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=150, temperature=0.7)