Updated inference.py

apps/inference.py

@@ -11,9 +11,7 @@ def load_model(masked_text,model_name):
 
     model = AutoModelForMaskedLM.from_pretrained(model_name, from_flax=True)
     tokenizer = AutoTokenizer.from_pretrained(model_name)
-    # tokenizer.save_pretrained('exported_pytorch_model')
-    # model.save_pretrained('exported_pytorch_model')
-    nlp = pipeline('fill-mask', model="exported_pytorch_model")
+    nlp = pipeline('fill-mask', model=model, tokenizer=tokenizer)
 
     result_sentence = nlp(masked_text)