T5
Collection
Originally from Google: Text-To-Text Transfer Transformer (T5)
•
4 items
•
Updated
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 shivaniNK8/t5-small-finetuned-cnn-news.
The calibration dataloader is the train dataloader. The default calibration sampling size 100 isn't divisible exactly by batch size 8, so the real sampling size is 104.
The linear modules lm.head, fall back to fp32 for less than 1% relative accuracy loss.
INT8 | FP32 | |
---|---|---|
Accuracy (eval-rouge1) | 38.9981 | 39.2142 |
Model size | 154M | 242M |
from optimum.intel import INCModelForSeq2SeqLM
model_id = "Intel/t5-small-finetuned-cnn-news-int8-dynamic"
int8_model = INCModelForSeq2SeqLM.from_pretrained(model_id)