This project is a **proof of concept** that aims to replicate the reasoning capabilities of OpenAI's newly released O1 model.

A package for sampling from Gibbs distributions during inference with LLMs.

A Chinese Open-Domain Dialogue System

Example models using DeepSpeed

Clustering for arbitrary data and dissimilarity function

Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥

OPD: Chinese Open-Domain Pre-trained Dialogue Model

Accessible large language models via k-bit quantization for PyTorch.

The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

Official codebase for "Distribution-Free, Risk-Controlling Prediction Sets"

Conformalized Quantile Regression

Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence technology。让每个人都简单方便的使用前沿人工智能技术

A library for building hierarchical text representation and corresponding downstream applications.

Python wrapper for the DPMMSubClusterStreaming.jl Julia package.

"DeepDPM: Deep Clustering With An Unknown Number of Clusters" [Ronen, Finder, and Freifeld, CVPR 2022]

Collecting research materials on EBM/EBL (Energy Based Models, Energy Based Learning)

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models

A library for uncertainty quantification based on PyTorch

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).

skweak: A software toolkit for weak supervision applied to NLP tasks

deepspeech on tensorflow (1.x ) and supported for tpu, gpu

Understanding and Improving Fast Adversarial Training [NeurIPS 2020]

A Discriminator Improves Text Generation without Updating the Generator

Optimus: the first large-scale pre-trained VAE language model

中文 预训练 ELECTRA 模型: 基于对抗学习 pretrain Chinese Model