leumastai/t5-large-quantized

By leumastai · ↓ 1 · ♥ 1 · Updated 2023-03-16

What's in this repo

This page lists the files in leumastai/t5-large-quantized, including t5-large-decoder-quantized.onnx, t5-large-encoder-quantized.onnx, t5-large-init-decoder-quantized.onnx.

3 ONNX models (.onnx files)
10 files, including 4 .json, 3 .onnx, 1 .md, 1 .model
Last updated 2023-03-16

ONNX files

File	Size	Download
t5-large-decoder-quantized.onnx	—	Download
t5-large-encoder-quantized.onnx	—	Download
t5-large-init-decoder-quantized.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

This repository contains quantized T5-large model. This model is 5x lesser than the T5-large model and also the inference time has been reduced by 3x on CPU, whilst giving impressive results.

Model info

transformers

transformers onnx t5 text2text-generation quantization en license:mit endpoints_compatible region:us

↓ 1 ♥ 1

Created: 2023-03-16

Updated: 2023-03-16

View on Hugging Face

Files (10)

.gitattributes

README.md

config.json

special_tokens_map.json

spiece.model

t5-large-decoder-quantized.onnx ONNX

t5-large-encoder-quantized.onnx ONNX

t5-large-init-decoder-quantized.onnx ONNX

tokenizer.json

tokenizer_config.json

Related models

More models

No task type declared.