Edit model card

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 import INCModelForSeq2SeqLM

model_id = "Intel/t5-base-cnn-dm-int8-dynamic"
int8_model = INCModelForSeq2SeqLM.from_pretrained(model_id)
Downloads last month
1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train Intel/t5-base-cnn-dm-int8-dynamic-inc

Collection including Intel/t5-base-cnn-dm-int8-dynamic-inc