Fastseq 基于ONNXRUNTIME的文本生成加速框架

Overview

Fastseq

基于ONNXRUNTIME的文本生成加速框架

1. 环境配置

# 创建onnx conda环境
conda create -n onnx_py38 python=3.8
conda activate onnx_py38
conda install pytorch cudatoolkit=10.2 -c pytorch

# 安装onnxruntime-gpu(目前只有1.5.2版本测试成功)
pip install onnxruntime-gpu==1.5.2

# 安装transformers==3.1.0版本
pip install transformers==3.1.0

2. ONNX转换

# 将huggingface保存的 模型/checkpoint 转换为onnx格式。这里使用onnxruntime自带的转换工具。
python -m onnxruntime.transformers.convert_to_onnx \
    -m "path_to_checkpoint/model_name(gpt2)" \
    --model_class GPT2LMHeadModel \
    --output gpt2_fp32.onnx \
    -p fp32

3. DEMO测试

CUDA_VISIBLE_DEVICES=3 python demo.py \
    --onnx_model_path "./gpt2_fp32.onnx" \
    --model_name_or_path "path_to_checkpoint" \
    --prompt_text "here is an example of gpt2 model" \
    --do_sample_top_k 5

4. TODO

  • TopK Decoding
  • Beam Search Decoding
  • INT8 Support
  • TensorRT Provider
  • ONNXRUNTIME Framework for BERT
  • Benchmark test
  • RESTful server demo
  • ONNXRUNTIME 1.8.1 Support
Owner
Jun Gao
Le vent se lève, il faut tenter de vivre.
Jun Gao
DANeS is an open-source E-newspaper dataset by collaboration between DATASET JSC (dataset.vn) and AIV Group (aivgroup.vn)

DANeS - Open-source E-newspaper dataset Source: Technology vector created by macrovector - www.freepik.com. DANeS is an open-source E-newspaper datase

DATASET .JSC 64 Aug 17, 2022
Transformer training code for sequential tasks

Sequential Transformer This is a code for training Transformers on sequential tasks such as language modeling. Unlike the original Transformer archite

Meta Research 578 Dec 13, 2022
Various Algorithms for Short Text Mining

Short Text Mining in Python Introduction This package shorttext is a Python package that facilitates supervised and unsupervised learning for short te

Kwan-Yuet 466 Dec 06, 2022
Codes for processing meeting summarization datasets AMI and ICSI.

Meeting Summarization Dataset Meeting plays an essential part in our daily life, which allows us to share information and collaborate with others. Wit

xcfeng 39 Dec 14, 2022
Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)

Bunkai Bunkai is a sentence boundary (SB) disambiguation tool for Japanese texts. Quick Start $ pip install bunkai $ echo -e '宿を予約しました♪!まだ2ヶ月も先だけど。早すぎ

Megagon Labs 160 Dec 23, 2022
The NewSHead dataset is a multi-doc headline dataset used in NHNet for training a headline summarization model.

This repository contains the raw dataset used in NHNet [1] for the task of News Story Headline Generation. The code of data processing and training is available under Tensorflow Models - NHNet.

Google Research Datasets 31 Jul 15, 2022
OceanScript is an Esoteric language used to encode and decode text into a formulation of characters

OceanScript is an Esoteric language used to encode and decode text into a formulation of characters - where the final result looks like waves in the ocean.

The following links explain a bit the idea of semantic search and how search mechanisms work by doing retrieve and rerank

Main Idea The following links explain a bit the idea of semantic search and how search mechanisms work by doing retrieve and rerank Semantic Search Re

Sergio Arnaud Gomez 2 Jan 28, 2022
Under the hood working of transformers, fine-tuning GPT-3 models, DeBERTa, vision models, and the start of Metaverse, using a variety of NLP platforms: Hugging Face, OpenAI API, Trax, and AllenNLP

Transformers-for-NLP-2nd-Edition @copyright 2022, Packt Publishing, Denis Rothman Contact me for any question you have on LinkedIn Get the book on Ama

Denis Rothman 150 Dec 23, 2022
Intent parsing and slot filling in PyTorch with seq2seq + attention

PyTorch Seq2Seq Intent Parsing Reframing intent parsing as a human - machine translation task. Work in progress successor to torch-seq2seq-intent-pars

Sean Robertson 159 Apr 04, 2022
Russian GPT3 models.

Russian GPT-3 models (ruGPT3XL, ruGPT3Large, ruGPT3Medium, ruGPT3Small) trained with 2048 sequence length with sparse and dense attention blocks. We also provide Russian GPT-2 large model (ruGPT2Larg

Sberbank AI 1.6k Jan 05, 2023
本插件是pcrjjc插件的重置版,可以独立于后端api运行

pcrjjc2 本插件是pcrjjc重置版,不需要使用其他后端api,但是需要自行配置客户端 本项目基于AGPL v3协议开源,由于项目特殊性,禁止基于本项目的任何商业行为 配置方法 环境需求:.net framework 4.5及以上 jre8 别忘了装jre8 别忘了装jre8 别忘了装jre8

132 Dec 26, 2022
SciBERT is a BERT model trained on scientific text.

SciBERT is a BERT model trained on scientific text.

AI2 1.2k Dec 24, 2022
Python library for Serbian Natural language processing (NLP)

SrbAI - Python biblioteka za procesiranje srpskog jezika SrbAI je projekat prikupljanja algoritama i modela za procesiranje srpskog jezika u jedinstve

Serbian AI Society 3 Nov 22, 2022
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet

Amazon Web Services - Labs 1.1k Dec 27, 2022
Random Directed Acyclic Graph Generator

DAG_Generator Random Directed Acyclic Graph Generator verison1.0 简介 工作流通常由DAG(有向无环图)来定义,其中每个计算任务$T_i$由一个顶点(node,task,vertex)表示。同时,任务之间的每个数据或控制依赖性由一条加权

Livion 17 Dec 27, 2022
Sentiment Analysis Project using Count Vectorizer and TF-IDF Vectorizer

Sentiment Analysis Project This project contains two sentiment analysis programs for Hotel Reviews using a Hotel Reviews dataset from Datafiniti. The

Simran Farrukh 0 Mar 28, 2022
Knowledge Graph,Question Answering System,基于知识图谱和向量检索的医疗诊断问答系统

Knowledge Graph,Question Answering System,基于知识图谱和向量检索的医疗诊断问答系统

wangle 823 Dec 28, 2022
A Multi-modal Model Chinese Spell Checker Released on ACL2021.

ReaLiSe ReaLiSe is a multi-modal Chinese spell checking model. This the office code for the paper Read, Listen, and See: Leveraging Multimodal Informa

DaDa 106 Dec 29, 2022