INT8 T5 base finetuned on CNN DailyMail
Post-training dynamic quantization
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model flax-community/t5-base-cnn-dm.
Evaluation result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-rougeLsum) | 36.5661 | 36.5959 |
| Model size | 326M | 892M |
Load with optimum:
from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSeq2SeqLM
int8_model = IncQuantizedModelForSeq2SeqLM.from_pretrained(
'Intel/t5-base-cnn-dm-int8-dynamic',
)
