Upload app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
 
 """
 Copied from inference in colab notebook
@@ -16,7 +17,7 @@ model_path = "Mat17892/t5small_enfr_opus"
 tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True, legacy=False)
 
 # Load the base model (e.g., LLaMA)
-base_model = AutoModelForSeq2SeqLM.from_pretrained(base_model)
+base_model = AutoModelForSeq2SeqLM.from_pretrained(base_model,token = os.getenv('huggingface_token'))
 
 # Load LoRA adapter
 from peft import PeftModel