Stars
Robust recipes to align language models with human and AI preferences
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Code for ACL2024 paper - Adversarial Preference Optimization (APO).
Train transformer language models with reinforcement learning.
A full pipeline to finetune Alpaca LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Alpaca architecture. Basically Chat…
Latex template for CUHK PhD Thesis
MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
A repository with several curated datasets of counter-narratives to fight online hate speech.
Chat with Meta's LLaMA models at home made easy
Making large AI models cheaper, faster and more accessible
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
AI agent stdlib that works with any LLM and TypeScript AI SDK.
❤️Emotional First Aid Dataset, 心理咨询问答、聊天机器人语料库
TensorFlow code and pre-trained models for BERT
[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
Codes for our paper "CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation" (ACL 2022)
Must-read Papers on Textual Adversarial Attack and Defense
A repository of concepts related to neural networks for NLP
Must-read papers on prompt-based tuning for pre-trained language models.
Unstructured Knowledge Access in Task-oriented Dialog Modeling using Language Inference, Knowledge Retrieval and Knowledge-Integrative Response Generation
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
NMFLibrary: Non-negative Matrix Factorization (NMF) Library: Version 2.1
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
With the aim of building next generation virtual assistants that can handle multimodal inputs and perform multimodal actions, we introduce two new datasets (both in the virtual shopping domain), th…