Machine Learning Engineering Open Book

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

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

A collection of learning resources for curious software engineers

Modeling, training, eval, and inference code for OLMo

A repository of links with advice related to grad school applications, research, phd etc

Fast and memory-efficient exact attention

ML Collections is a library of Python Collections designed for ML use cases.

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

Erasing concepts from neural representations with provable guarantees

An efficient video loader for deep learning with smart shuffling that's super easy to digest

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

Easily compute clip embeddings and build a clip retrieval system with them

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

🤖 A PyTorch library of curated Transformer models and their composable components

[ICCV2023 Oral] Unmasked Teacher: Towards Training-Efficient Video Foundation Models

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Efficient few-shot learning with Sentence Transformers

Minimal keyword extraction with BERT

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"

QLoRA: Efficient Finetuning of Quantized LLMs

A curated list of data oriented design resources.

A component orchestration engine

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities