Upload app.py with huggingface_hub

app.py

@@ -9,9 +9,16 @@ import torch.nn.functional as F
 import time
 import json
 import os
+from huggingface_hub import login
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 
+# Login with HF token from Space secrets (needed for gated models like Gemma)
+HF_TOKEN = os.environ.get("HF_TOKEN")
+if HF_TOKEN:
+    login(token=HF_TOKEN)
+    print("Logged in to HuggingFace")
+
 # ─── Configuration ───
 MODEL_CONFIGS = {
     "Gemma-270M (Fastest)": {