Table 11 Latency and throughput benchmarks for transformer models.
From: Classifying human vs. AI text with machine learning and explainable transformer models
Model | Avg latency (s/prediction) | Throughput (texts/s) |
|---|---|---|
XLM-RoBERTa | 0.2893 | 69.1 |
BERT | 0.3163 | 63.2 |
RoBERTa | 0.2935 | 68.1 |
