hit-computer

MTA-LSTM

The code and data of ijcai2018 paper <Topic-to-Essay Generation with Neural Networks>

char-rnn-tf

Implement character-level language models for text generation based-on LSTM, in Python/TensorFlow

SC-LSTM

Implement SC-LSTM model for text generation in control of words, in Python/TensorFlow

char-rnn

Recurrent Neural Networks(GRU) for character-level language models on Chinese, in Python/Theano

GRU-or-CNN

Implement GRU or CNN in python/theano to learn the sentences representation for coherence, answer selecting or dialogue.

Algorithm

algorithm and data structure

Tag-Suggestion

Implement CNN-GRU hierarchical model in Python/Theano for text tag suggestion

Phrase2Vec

Learn the distributed representation of phrase and word

CPU-Design

Use VHDL language to design the simple CPU.

Compiler

Experiments in the course of Compiling Principles and carry out it

BanditsBook

Code for my book on Multi-Armed Bandit Algorithms

MH

Metropolis-Hastings Algorithm

AliceMind

char-rnn-1

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

chat_corpus

chat corpus collection from various open sources

ColossalAI

Making big AI models cheaper, easier, and more scalable

GLM

GLM (General Language Model)

hit-computer.github.io

personal blog

Kaggle_HomeDepot

Turing Test's Solution for Home Depot Product Search Relevance Competition on Kaggle (https://www.kaggle.com/c/home-depot-product-search-relevance)

models

Models built with TensorFlow

Pretrained-Language-Model

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

pytorch-onnx-tensorflow-pb

Converting A PyTorch Model to Tensorflow pb using ONNX

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

SeqGAN

Implementation of Sequence Generative Adversarial Nets with Policy Gradient

smoothquant

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Theano

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

topicvec

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Travel_By_Movie

Weibo Application

xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.