jiaangli

Awesome-Interpretability-in-Large-Language-Models

This repository collects all relevant resources about interpretability in LLMs

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Multimodal-AND-Large-Language-Models

Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.

bib_cleaner

Bib Cleaner removes unnecessary entries from your bib files.

build-nanogpt

Video+code lecture on building nanoGPT from scratch

aclpubcheck

Tools for checking ACL paper submissions

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

LLM101n

LLM101n: Let's build a Storyteller

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

LLM-Finetuning

LLM Finetuning with peft

LLMSurvey

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

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

dspy

DSPy: The framework for programming—not prompting—foundation models

transformer-debugger

EasyEdit

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

arxiv-submission-sanitizer-flattener

Simple Python scripts to clean up and flatten ArXiv LaTeX submissions.

TransformerLens

A library for mechanistic interpretability of GPT-style language models

world-models

Extracting spatial and temporal world models from LLMs

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

THINGS-data

THINGS-data: A multimodal collection of large-scale datasets for investigating object representations in brain and behavior

langchain-

LangChain 的中文入门教程

bilivideos

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

vllm

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

Mr.-Ranedeer-AI-Tutor

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

RecurrentGPT

Official Code for Paper: RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

MathTranslate

translate scientific papers in latex, especially arxiv papers