Qian

A framework for the evaluation of autoregressive code generation language models.

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

A blog for understanding graph neural network

The code of ACL 2020 paper "You Impress Me: Dialogue Generation via Mutual Persona Perception"

A lightweight script for processing HTML page to markdown format with support for code blocks

北航小操作系统实验指导书

BUAA 2015 Compiler Project

No description.

public dataset for followup-query analysis, accepted by AAAI2019

阿超的四则运算生成器 v1.0

A auto test framework for project sudoku

No description.

ACL 2019论文复现：Improving Multi-turn Dialogue Modelling with Utterance ReWriter

No description.

Build To Win

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

No description.

Papers about Context-dependent Semantic Parsing

The design for database of buaa. 2016/1/3

Synthetic Data Generation for Evaluation

No description.

Adaptation of gxemul to support the CHERI MIPS unit test suite and certain CHERI features

No description.

Revisiting Mid-training in the Era of Reinforcement Learning Scaling

This repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc

Fine-tune SantaCoder for Code/Text Generation.

This repository contains a collection of papers and resources on Reasoning in Large Language Models.

No description.

No description.

My vim config

Minimal MVVM UWP App with CRUD over Data Service

software engineering tools

No description.

C# wrapper around excellent wkhtmltopdf console utility.

备份cnblogs的博客

WinRT XAML Toolkit

A cross-platform plotting library for .NET

No description.

No description.

Microsoft.Recognizers.Text.Number provides robust recognition and resolution of numbers expressed in English, Spanish and Chinese.

Schema-Guided Dialogue State Tracking

:fire: 一款专注于阅读的博客园主题

Buaa Os lab3

BiLSTM-CRF joint model for tasks like sequence labeling using char/word level embeddings in Tensorflow

BUAA,OSLAb6

Puzzles for learning Triton

verl: Volcano Engine Reinforcement Learning for LLMs

2019年北航暑期软件工程培训-预培训项目仓库

No description.

Defeating the Training-Inference Mismatch via FP16

✨ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com

No description.

Accurate line-level text detection and recognition (OCR) in any language

Async pipelined version of Verl

No description.

Deep Learning for Code Website

A high-throughput and memory-efficient inference and serving engine for LLMs

🌾 OAT: Online AlignmenT for LLMs

更纯粹、更高压缩率的Tokenizer

Go ahead and axolotl questions

DataComp for Language Models

Extract a single expert from an MoE model of Mixtral architecture, using slerp

Data Toolkit for Sailor Language Models

This project studies the performance and robustness of language models and task-adaptation methods.

Tools for merging pretrained large language models.

YT_subtitles - extracts subtitles from YouTube videos to raw text for Language Model training

OpenAgents: An Open Platform for Language Agents in the Wild

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

distributed trainer for LLMs

Infinite Photorealistic Worlds using Procedural Generation

A guidance language for controlling large language models.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

No description.

No description.

The prime repository for state-of-the-art Multilingual Question Answering research and development.

Ongoing research training transformer models at scale

No description.

No description.

Drive a browser with GPT-3

code for the NAACL 2021 paper Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention by Microsoft Semantic Machines.

personal online resume

PyTorch original implementation of Cross-lingual Language Model Pretraining.

No description.

Exploring Few-Shot Adaptation of Language Models with Tables

TAPEX: Table Pre-training via Learning a Neural SQL Executor

TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-world financial reports.

Fully-automated scripts for collecting AI-related papers

Official repository of ICLR 2022 paper FILM: Following Instructions in Language with Modular Methods

ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.

Public repo for HF blog posts

No description.

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

A large annotated semantic parsing corpus for developing natural language interfaces.

the resum of siviltaram

No description.

Experiment for lsat

This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX

The official implementation of EMNLP 2020, "A Simple and Effective Model for Answering Multi-span Questions".

The official tool for creating proceedings for conferences of the Association for Computational Linguistics (ACL).

No description.

Data and Code for ICLR2020 Paper "TabFact: A Large-scale Dataset for Table-based Fact Verification"

Prefix-Tuning: Optimizing Continuous Prompts for Generation

Code and dataset "ZEST" from "Learning from task descriptions", Weller et al, EMNLP 2020

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Author implementation of the paper "Don’t paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing"

The Open edX platform, the software that powers edX!

No description.

No description.

整理AI相关领域的一些综述

Officially supported AllenNLP models

ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table cells, produce a one-sentence description. We hope it can serve as a useful research benchmark for high-precision conditional text generation.

Data and Code Release for "On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries"

This repo includes extensions to the Stanford Dialogue Corpus. It contains crowd-sourced rewrites to facilitate research in dialogue state tracking using natural language as the interface.

Code for the paper: Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations

Code to reproduce experiments in the paper "Task-Oriented Dialogue as Dataflow Synthesis" (TACL 2020).

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A relation-aware semantic parsing model from English to SQL

CRF-RNN PyTorch version http://crfasrnn.torr.vision

OpenAI gpt classification fine-tuning example.

Span-based system for named entity, relation, and event extraction.

No description.

Generalizing Natural Language Analysis through Span-relation Representations

Simple language-driven navigation tasks for studying compositional learning

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Code for "Learning Compositional Rules via Neural Program Synthesis"

Humans understand novel sentences by composing meanings and roles of core language components. In contrast, neural network models for natural language modeling fail when such compositional generalization is required. The main contribution of this paper is to hypothesize that language compositionality is a form of group-equivariance. Based on this hypothesis, we propose a set of tools for constructing equivariant sequence-to-sequence models. Throughout a variety of experiments on the SCAN tasks, we analyze the behavior of existing models under the lens of equivariance, and demonstrate that our equivariant architecture is able to achieve the type compositional generalization required in human language understanding.

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

No description.

A simple solution for the first stage candidate serach in the real system of retrieval chatbot.

This repo contains the code for our paper "EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing" accepted at ACL 2019.

Chinese medical dialogue data 中文医疗对话数据集

Open Source Neural Machine Translation in PyTorch

No description.

This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, and word order information for the problem of paraphrase identification.

A framework for building semantic parsers (including neural module networks) with AllenNLP, built by the authors of AllenNLP

100+ Chinese Word Vectors 上百种预训练中文词向量

No description.

Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs(EMNLP2019)

Open source text annotation tool for machine learning practitioner.

Question-in-context rewriting

Source code and dataset for the paper "GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue" (Jun Quan, Deyi Xiong, Bonnie Webber and Changjian Hu. EMNLP, 2019)

Graph Neural Networks for Natural Language Processing tutorial at EMNLP 2019

Codes for <CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling>

Fully Statistical Neural Belief Tracker (Mrkšić and Vulić, ACL 2018)

Example code for "Real-World Natural Language Processing"

Neural Logic Reasoning for Question Answering

PyTorch implementation of the ACL 2019 paper "Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader"

code for semantic parsing model "HSP" in paper "Complex Question Decomposition for Semantic Parsing".

static-dir files for a simple-server demo with ReactJS visualizations

Caffe code to accompany my Tutorial on Variational Autoencoders

This repository stores slides for a tutorial on variational inference for NLP audiences.

[EMNLP 2018] On Tree-Based Neural Sentence Modeling.

Windows version of NVIDIA's NCCL ('Nickel') for multi-GPU training - please use https://github.com/NVIDIA/nccl for changes.

Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction - ACL 2019

XLNet: Generalized Autoregressive Pretraining for Language Understanding

No description.

What My Deep Model Doesn't Know...

No description.

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

No description.

A BERT model for scientific text.

🦄 State-of-the-Art Conversational AI with Transfer Learning

QnA bot powered by CoQA + BERT

🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

Deep Reinforcement Learning For Sequence to Sequence Models

A PyTorch implementation of Transformer in "Attention is All You Need"

Search-based-Neural-Structured-Learning-for-Sequential-Question-Answering

An open-source NLP research library, built on PyTorch.

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

MatchZoo is a toolkit for text matching. It was developed to facilitate the designing, comparing, and sharing of deep text matching models.

No description.

BUAA OSLab4

No description.

Tensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character/word embeddings

No description.

pytorch-seq2seq is a framework for sequence-to-sequence (seq2seq) models in PyTorch.

A pytorch implementation of Reading Wikipedia to Answer Open-Domain Questions.

A chainer implementation of Memory Augmented Neural Network

One Shot Learning using Memory-Augmented Neural Networks based on Neural Turing Machine architecture in Tensorflow

A simple chat application that demonstrates how to structure a Flask-SocketIO application.

ChatterBot is a machine learning, conversational dialog engine.

A complete and graceful API for Wechat. 微信个人号接口（支持文件、图片上下载）、微信机器人及命令行微信。三十行即可自定义个人号机器人。

:deciduous_tree:从中文文本中自动提取关键词和摘要

No description.

编写一个博客 web app，从中实现一个自己的web 框架

轻量级微信企业号开发框架

Fast C++ prime counting function implementation

An elegant \LaTeX\ résumé template

用LaTeX制作优雅的中文个人简历，适合IT从业者。FontAwesome字体+Adobe字体+有照片和无照片版本，总有一款适合你。

网页版微信API，包含终端版微信及微信机器人

NLTK Source

Stanford NLP for .NET

This repo contains code samples using .NET Core, which run on Windows, Mac OS and Ubuntu.

Windows UI Dev Labs the place for getting the latest code samples and demos using Windows.UI.Xaml and Windows.UI.Composition to make beautiful Universal Windows Platform applications.

No description.

A demo about Universal Windows Platform APP about network, focusing on socketstream.

A UWP Demo in learning.

It is a platform to write your own OS kernel,its based on Linux Kernel 3.9.4 source code.