Swapping to ONNX.

app.py

@@ -1,8 +1,21 @@
 import gradio as gr
 
-from transformers import pipeline
+from transformers import AutoTokenizer, pipeline
+from optimum.onnxruntime import ORTModelForSequenceClassification
 
-classifier = pipeline("text-classification", model="SamLowe/roberta-base-go_emotions")
+model_id = "SamLowe/roberta-base-go_emotions-onnx"
+file_name = "onnx/model_quantized.onnx"
+
+model = ORTModelForSequenceClassification.from_pretrained(model_id, file_name=file_name)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+classifier = pipeline(
+    task="text-classification",
+    model=model,
+    tokenizer=tokenizer,
+    top_k=None,
+    function_to_apply="sigmoid",  # optional as is the default for the task
+)
 
 def predict(text):
     result = classifier(text)

requirements.txt

@@ -1,3 +1,5 @@
 torch==2.4.0
 huggingface_hub==0.26.0
-transformers==4.36
+transformers==4.36
+onnxruntime==1.18.1
+optimum==1.21.3