GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → lipiji → Guyu

lipiji / Guyu

Licence: mit
pre-training and fine-tuning framework for text generation

Programming Languages

python
139335 projects - #7 most used programming language

Labels

nlptext-generation

Projects that are alternatives of or similar to Guyu

Textgenrnn
Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.
Stars: ✭ 4,584 (+3083.33%)
Mutual labels:  text-generation
Gpt2 French
GPT-2 French demo | Démo française de GPT-2
Stars: ✭ 47 (-67.36%)
Mutual labels:  text-generation
Delta
DELTA is a deep learning based natural language and speech processing platform.
Stars: ✭ 1,479 (+927.08%)
Mutual labels:  text-generation
Leakgan
The codes of paper "Long Text Generation via Adversarial Training with Leaked Information" on AAAI 2018. Text generation using GAN and Hierarchical Reinforcement Learning.
Stars: ✭ 533 (+270.14%)
Mutual labels:  text-generation
Concise Ipython Notebooks For Deep Learning
Ipython Notebooks for solving problems like classification, segmentation, generation using latest Deep learning algorithms on different publicly available text and image data-sets.
Stars: ✭ 23 (-84.03%)
Mutual labels:  text-generation
Market Reporter
Automatic Generation of Brief Summaries of Time-Series Data
Stars: ✭ 54 (-62.5%)
Mutual labels:  text-generation
Paperrobot
Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
Stars: ✭ 372 (+158.33%)
Mutual labels:  text-generation
Kogpt2 Finetuning
🔥 Korean GPT-2, KoGPT2 FineTuning cased. 한국어 가사 데이터 학습 🔥
Stars: ✭ 124 (-13.89%)
Mutual labels:  text-generation
Describing a knowledge base
Code for Describing a Knowledge Base
Stars: ✭ 42 (-70.83%)
Mutual labels:  text-generation
Gpt2 Chitchat
GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)
Stars: ✭ 1,230 (+754.17%)
Mutual labels:  text-generation
Cdial Gpt
A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models
Stars: ✭ 596 (+313.89%)
Mutual labels:  text-generation
Grover
Code for Defending Against Neural Fake News, https://rowanzellers.com/grover/
Stars: ✭ 774 (+437.5%)
Mutual labels:  text-generation
Markov
A generic markov chain implementation in Rust.
Stars: ✭ 59 (-59.03%)
Mutual labels:  text-generation
Textgan Pytorch
TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
Stars: ✭ 479 (+232.64%)
Mutual labels:  text-generation
Kadot
Kadot, the unsupervised natural language processing library.
Stars: ✭ 108 (-25%)
Mutual labels:  text-generation
Gpt2 Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
Stars: ✭ 4,592 (+3088.89%)
Mutual labels:  text-generation
Gpt2 Ml
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
Stars: ✭ 1,066 (+640.28%)
Mutual labels:  text-generation
Onnxt5
Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
Stars: ✭ 143 (-0.69%)
Mutual labels:  text-generation
Tensorflow Nlp
NLP and Text Generation Experiments in TensorFlow 2.x / 1.x
Stars: ✭ 1,487 (+932.64%)
Mutual labels:  text-generation
Dialogpt
Large-scale pretraining for dialogue
Stars: ✭ 1,177 (+717.36%)
Mutual labels:  text-generation
View All Similar Projects ➔

Guyu (谷雨)

pre-training and fine-tuning framework for text generation

backbone code for "An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation": https://arxiv.org/abs/2003.04195

@article{DBLP:journals/corr/abs-2003-04195,
  author    = {Piji Li},
  title     = {An Empirical Investigation of Pre-Trained Transformer Language Models
               for Open-Domain Dialogue Generation},
  journal   = {CoRR},
  volume    = {abs/2003.04195},
  year      = {2020},
  url       = {https://arxiv.org/abs/2003.04195},
  archivePrefix = {arXiv},
  eprint    = {2003.04195},
  timestamp = {Tue, 10 Mar 2020 13:33:48 +0100}}
}

torch>=1.0

Pre-training:

./prepare_data.sh
./train.sh
./inference.sh

Fine-tuning

Example: chat-bot

cd chat_bot
./prepare_data.sh
./fine_tune.sh
./inference.sh

Web Api:

./deploy.sh

Pre-trained models

  • 12-layer, 768-hidden, 12-heads, Chinese (News + zhwiki, 200G) and English (Gigawords + Bookscorpus + enwiki, 60G)

  • 24-layer, 768-hidden, 12-heads, Chinese (News + zhwiki, 200G) and English (Gigawords + Bookscorpus + enwiki, 60G)

  • download them: https://github.com/lipiji/Guyu/tree/master/model

References:

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].