QZ

jepa-wms. Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**

openpi. Python

LeafLink. LeafLink is a lightweight CLI tool for syncing local LaTeX projects with Overleaf, featuring pull/push workflows and pseudo real-time collaboration.

BridgeDepth. [ICCV 2025 Highlight] BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment

MonSter. 【CVPR 2025 Highlight】MonSter: Marry Monodepth to Stereo Unleashes Power

Embodied_AI_Paper_List. [Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

YJYpaper. 一个用来记录武汉大学杨景媛论文问题的仓库

hurtlex. A multilingual lexicon of words to hurt.

hate-speech-lexicons. Useful resources for hate speech detection

Sentiment-Reasoning. [ACL 2025 Industry Track, Oral] Sentiment Reasoning for Healthcare

neuronpedia. open source interpretability platform 🧠

nnsight. The nnsight package enables interpreting and manipulating the internals of deep learned models.

SAELens. Training Sparse Autoencoders on Language Models

TransformerLens. A library for mechanistic interpretability of GPT-style language models

circuit-tracer. Python

ICLR2024-OpenReviewData. Crawl & Visualize ICLR 2024 Data from OpenReview

deciphering_cot. [EMNLP 2024 Findings] Code for deciphering CoT using shift ciphers

MemPi. localize a memorized sequence in LLMs (NAACL 2024)

dataset. Multi30k Dataset

semantic-memorization. Jupyter Notebook

NSFC-application-template-latex. 国家自然科学基金申请书正文（面上项目）LaTeX 模板（非官方）

numeric-property-repr. Code for the paper: Monotonic Representation of Numeric Properties in Language Models (ACL 2024)

FreeCtrl. Python

SpinQuant. Code repo for the paper "SpinQuant LLM quantization with learned rotations"

CAA. Steering Llama 2 with Contrastive Activation Addition

sensitivity-hardness. Code for the paper

ML4RoadSafety. A dataset for traffic accident analysis in the US

Same-Task-More-Tokens. The code for the paper: "Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models"

semiring-backprop-exps. Jupyter Notebook

dolma. Data and tools for generating and inspecting OLMo pre-training data.

massive-activations. Code accompanying the paper "Massive Activations in Large Language Models"

awesome-mechanistic-interpretability-lm-papers.

ff-layers. The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. EMNLP, 2021.

platonic-rep. Python

AI-Scientist. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

neuron-analysis-cot-arithmetic-reasoning. Python

QSLAW. The official code for "Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation" | [MM2024]

diagNNose. diagNNose is a Python library that facilitates a broad set of tools for analysing hidden activations of neural models.

SCAPT-ABSA. Code for EMNLP 2021 paper: "Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training"

XICL. HTML

LLM-Sentiment. [NAACL 2024] Data and code for our paper "Sentiment Analysis in the Era of Large Language Models: A Reality Check"

LLM101n. LLM101n: Let's build a Storyteller

llm_interview_note. 主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Interpret_Instruction_Tuning_LLMs. Understanding Why and How Instruction Tuning Changes Pre-trained Models

heldout-influence-estimation. Python

AQuA. A algebraic word problem dataset, with multiple choice questions annotated with rationales.

Artificial-Intelligence-Terminology-Database. A comprehensive mapping database of English to Chinese technical vocabulary in the artificial intelligence domain

awesome_Chinese_medical_NLP. 中文医学NLP公开资源整理：术语集/语料库/词向量/预训练模型/知识图谱/命名实体识别/QA/信息抽取/模型/论文/etc

KEPT. auto icd coding with prompt

MIMIC-IV-ICD-data-processing. Jupyter Notebook

medical-coding-reproducibility. Jupyter Notebook

BioT5. BioT5 (EMNLP 2023) and BioT5+ (ACL 2024 Findings)

OpenBioMed. Python

Scientific-LLM-Survey. Scientific Large Language Models: A Survey on Biological & Chemical Domains

chain-of-thought. Research papers about Chain of Thought (CoT)

beir. A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

ragas. Supercharge Your LLM Application Evaluations 🚀

AutoGPT. 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.

ChatGLM-Efficient-Tuning. Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

machine-learning-interview. 算法工程师-机器学习面试题总结

LLMs_interview_notes. 该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

ebert. Python

idiomem. Python

lm-extraction-benchmark. Python

LM_Memorization. Training data extraction on GPT-2

reversal_curse. Python

BUAAThesis. 北航研究生学位论文模板（Word+LaTeX）.

aigc. 《构筑大语言模型应用：应用开发与架构设计》一本关于 LLM 在真实世界应用的开源电子书，介绍了大语言模型的基础知识和应用，以及如何构建自己的模型。其中包括Prompt的编写、开发和管理，探索最好的大语言模型能带来什么，以及LLM应用开发的模式和架构设计。

AGIEval. Python

meerkat. Explore and understand your training and validation data.

Code-LMs. Guide to using pre-trained large language models of source code

modelzoo. Python

zeno-build. Build, evaluate, understand, and fix LLM-based apps

DPL. Python

SSEGCN-ABSA. SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis

AspectBasedSentimentAnalysis. Aspect Based Sentiment Analysis is a special type of sentiment analysis. In an explicit aspect, opinion is expressed on a target(opinion target), this aspect-polarity extraction is known as ABSA.

Aspect-Based-Sentiment-Analysis. A paper list for aspect based sentiment analysis.

fine-grained-sentiment. A comparison and discussion of different NLP methods for 5-class sentiment classification on the SST-5 dataset.

prm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems

RWKV-LM. RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

ChatRWKV. ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

FactualityPrompt. Python

language. Shared repository for open-sourced projects from the Google AI Language team.

crosslingual_winograd. "It's All in the Heads" (Findings of ACL 2021), official implementation and data

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.

XED. XED multilingual emotion datasets

ChatALL. Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vicuna, Claude, ChatGLM, MOSS, 讯飞星火, 文心一言 and more, discover the best answers

learning_research. 本人的科研经验

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

OpenAlpaca. OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA

open_llama. OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

awesome-instruction-dataset. A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

LLM-Zoo. LLM Zoo collects information of various open- and close-sourced LLMs

anthropic-sdk-python. Python

SVAMP. NAACL 2021: Are NLP Models really able to Solve Simple Math Word Problems?

HumanPrompt. A framework for human-readable prompt-based method with large language models. Specially designed for researchers. (Deprecated, check out LangChain for better usage!)

ml-mkqa. We introduce MKQA, an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The goal of this dataset is to provide a challenging benchmark for question answering quality across a wide set of languages. Please refer to our paper for details, MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering

llama-chat. Chat with Meta's LLaMA models at home made easy

evals. Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.

pythia. The hub for EleutherAI's work on interpretability and learning dynamics

dolly. Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

RedPajama-Data. The RedPajama-Data repository contains code for preparing large datasets for training large language models.

CommitmentBank. Materials related to our Sinn und Bedeutung 23 paper

url-nlp. Python

realtimeqa_public. Python

exams-qa. A Multi-subject High School Examinations Dataset for Cross-lingual and Multilingual Question Answering

MLQA. New dataset

xquad.

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

lmql. A language for constraint-guided and efficient LLM programming.

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

Semantic-Segment-Anything. Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

JARVIS. JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

BIG-bench. Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

lm-evaluation-harness. A framework for few-shot evaluation of language models.

perspectiveapi. Perspective is an API that uses machine learning models to score the perceived impact a comment might have on a conversation. See https://developers.perspectiveapi.com for more information.

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

BELLE. BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

grade-school-math. Python

real-toxicity-prompts. Jupyter Notebook

TruthfulQA. TruthfulQA: Measuring How Models Imitate Human Falsehoods

alpaca-lora. Instruct-tune LLaMA on consumer hardware

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

pyllama. LLaMA: Open and Efficient Foundation Language Models

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

OpenChatKit. Python

optimate. A collection of libraries to optimise AI model performances

Awesome-ChatGPT. ChatGPT资料汇总学习，持续更新......

minimal-llama. Python

ChatGPT-Official. ChatGPT Client using official OpenAI API

PyGPT. Python implementation of Unofficial ChatGPT Client

chatllama. ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT

GEMBA. GEMBA — GPT Estimation Metric Based Assessment

LLM-Augmenter.

TaskMatrix. Python

metaseq. Repo for external large-scale work

CodeGen. CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.

llama. Inference code for Llama models

MaxwelsDonc.

mozart. [COLING 2022] Data for our paper "Are Pretrained Multilingual Models Equally Fair Across Languages?"

following-instructions-human-feedback.

summarize-from-feedback. Code for "Learning to summarize from human feedback"

lm-human-preferences. Code for the paper Fine-Tuning Language Models from Human Preferences

crows-pairs. This repository contains the data and code introduced in the paper "CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models" (EMNLP 2020).

sentence-prediction. Python

PoLitBert. Polish RoBERTA model trained on Polish literature, Wikipedia, and Oscar. The major assumption is that quality text will give a good model.

transformer_grammars. Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale, TACL (2022)

detect-SCC. Detecting Strongly Connected Components for Scholarly Data

cramming. Cramming the training of a (BERT-type) language model into limited compute.

notebooks. Interactive Jupyter Notebooks for learning materials

wiki_parse. Tools for multilingual constiuency / dependency parsing of wiki*.

stanford-openie-python. Stanford Open Information Extraction made simple!

enhanced-subject-verb-object-extraction. Enhanced Subject Word Object Extraction

fastText. Library for fast text representation and classification.

responsibleNLPresearch. templates and other documents regarding responsible NLP research

WAX. The respository describing a novel datasets for word association explanations

order_position. Python

sentence-transformers-for-analogies. Jupyter Notebook

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

ivy. Convert Machine Learning Code Between Frameworks

aclpubcheck. Tools for checking ACL paper submissions

Research. novel deep learning research works with PaddlePaddle

wordnet-randomwalk-python. Repository of code used for WordNet random walk embedding experiments

robustLM. Code for paper "Better Language Model with Hypernym Class Prediction"

sense-bert. This is the code for loading the SenseBERT model, described in our paper from ACL 2020.

LIBERT. Code from the paper "Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity"

KTNET. Python

nltk_data. NLTK Data

sentime. Ensemble Approach to Extract Sentiments from Tweets or Product Reviews

entity2vec. Generates a set of property-specific entity embeddings from knowledge graphs using node2vec

ACL2022_KnowledgeNLP_Tutorial. Materials for ACL-2022 tutorial: Knowledge-Augmented Methods for Natural Language Processing

MRFN. Tensorflow implementation for MRFN in Retrieval-based Chatbots

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

AllenNLP-Tutorials-Chinese. 中文AllenNLP教程（持续更新）

allennlp-tutorials. a detail tutorials of allennlp , which is based on my own view.

gensen. Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning

spaCy. 💫 Industrial-strength Natural Language Processing (NLP) in Python

kb. KnowBert -- Knowledge Enhanced Contextual Word Representations

evaluate. 🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

KILT. Library for Knowledge Intensive Language Tasks

KESA. The source code of KESA

Paper-Writing-Tips. MLNLP社区用来帮助大家避免论文投稿小错误的整理仓库。 Paper Writing Tips

prompt-vr. Jupyter Notebook

OTT-QA. Code and Data for ICLR2021 Paper "Open Question Answering over Tables and Text"

Wikipedia_annotator. Wikipedia plain text, anchors and their positions, associated entities extractor

alphafold. Open source code for AlphaFold 2.

Annotated-WikiExtractor. Simple Wikipedia plain text extractor with article link annotations and Hadoop support.

KGPT. Code and Data for EMNLP2020 Paper "KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation"

Variational-Vocabulary-Selection. Code for NAACL19 Paper "How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection"

el-helpfulness-dataset. A dataset used in the paper "Evaluating the Helpfulness of Linked Entities to Readers"

textent. Representation Learning of Entities and Documents from Knowledge Base Descriptions

wikipedia-nlp. Sample code for natural language processing using Wikipedia

KnowledgeCorpus. Some corpus used for pre-training entity- or description-related tasks

DisExtract. The library that uses dependency parsing to preprocess text to train DisSent model