| language: en | |
| tags: | |
| - bert | |
| - rte | |
| - glue | |
| - torchdistill | |
| - nlp | |
| - int8 | |
| - neural-compressor | |
| - Intel® Neural Compressor | |
| - text-classfication | |
| - PostTrainingStatic | |
| license: apache-2.0 | |
| datasets: | |
| - rte | |
| metrics: | |
| - f1 | |
| # INT8 bert-large-uncased-rte-int8-static | |
| ## Post-training static quantization | |
| ### PyTorch | |
| This is an INT8 PyTorch model quantized with [Intel® Neural Compressor](https://github.com/intel/neural-compressor). | |
| The original fp32 model comes from the fine-tuned model [yoshitomo-matsubara/bert-large-uncased-rte](https://huggingface.co/yoshitomo-matsubara/bert-large-uncased-rte). | |
| #### Test result | |
| | |INT8|FP32| | |
| |---|:---:|:---:| | |
| | **Accuracy (eval-f1)** |0.7365|0.7401| | |
| | **Model size (MB)** |1244|1349| | |
| #### Load with Intel® Neural Compressor: | |
| ```python | |
| from optimum.intel import INCModelForSequenceClassification | |
| model_id = "Intel/bert-large-uncased-rte-int8-static" | |
| int8_model = INCModelForSequenceClassification.from_pretrained(model_id) | |
| ``` | |