optimum usage

app.py

@@ -1,12 +1,26 @@
+# import gradio as gr
+# from transformers import AutoTokenizer, AutoModelForSequenceClassification
+# import torch
+
+# device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+# model_id = "Rahmat82/DistilBERT-finetuned-on-emotion"
+# tokenizer = AutoTokenizer.from_pretrained(model_id, return_tensors="pt", use_fast=True)
+# model = AutoModelForSequenceClassification.from_pretrained(model_id)
+# model.to(device)
+
+
+
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import pipeline, AutoTokenizer
+from optimum.onnxruntime import ORTModelForSequenceClassification
 import torch
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
-model_id = "Rahmat82/DistilBERT-finetuned-on-emotion"
-tokenizer = AutoTokenizer.from_pretrained(model_id, return_tensors="pt", use_fast=True)
-model = AutoModelForSequenceClassification.from_pretrained(model_id)
+model_name = "Rahmat82/DistilBERT-finetuned-on-emotion"
+model = ORTModelForSequenceClassification.from_pretrained(model_name, export=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
 model.to(device)
 
 def predict(query: str) -> dict: