The official GitHub page for the survey paper "A Survey of Large Language Models".

https://acl2023-retrieval-lm.github.io/

Homepage

PromptBERT: Improving BERT Sentence Embeddings with Prompts

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

Instruction Tuning with GPT-4

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

《面向开发者的 ChatGPT 提示词工程》非官方版中英双语字幕 Unofficial subtitles of "ChatGPT Prompt Engineering for Developers"

ChatGPT相关资源汇总

Just a bunch of script to summary book and document using LLM

Code for "Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (EMNLP 2022)"

人工精调的中文对话数据集和一段chatglm的微调代码

Methods and Implements of Deep Clustering

DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue

基于向量数据库与GPT3.5的通用本地知识库方案(A universal local knowledge base solution based on vector database and GPT3.5)

Inference code for LLaMA models

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

Data augmentation for NLP

Anomaly detection related books, papers, videos, and toolboxes

Must-read papers on prompt-based tuning for pre-trained language models.

Pytorch implementation of Supporting Clustering with Contrastive Learning, NAACL 2021

基于法律裁判文书的事件抽取及其应用，包括数据的分词、词性标注、命名实体识别、事件要素抽取和判决结果预测等内容

Deep Reinforcement Learning

An experiment and demo-level tool for text information extraction (event-triples extraction), which can be a route to the event chain and topic graph, 基于依存句法与语义角色标注的事件三元组抽取，可用于文本理解如文档主题链，事件线等应用。

Winning solution for the Kaggle Feedback Prize Challenge.

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"