INT8 T5 small finetuned on XSum
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 adasnew/t5-small-xsum.
The linear modules lm.head, fall back to fp32 for less than 1% relative accuracy loss.
Evaluation result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-rouge1) | 29.9008 | 29.9592 |
| Model size | 154M | 242M |
Load with optimum:
from optimum.intel import INCModelForSeq2SeqLM
model_id = "Intel/t5-small-xsum-int8-dynamic-inc"
int8_model = INCModelForSeq2SeqLM.from_pretrained(model_id)