[NeurIPS'25] GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Implementation and evaluation of Scaling Embedding Layers in Language Models research paper

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text

[ICLR'24 Spotlight] DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

Package to compute Mauve, a similarity score between neural text and human text. Install with `pip install mauve-text`.

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Guidelime: A WoW Classic addon for leveling guides with automatic progress updates

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

v2ray傻瓜式一键部署脚本

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Differentially-private transformers using HuggingFace and Opacus

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

open-source agentic AI data assistant for the next generation of AI + Data products.

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

Private Evolution: Generating DP Synthetic Data without Model Training [ICML 2026, ICLR 2024, ICML 2024 Spotlight]

Inference code for LLaMA models in JAX

An ML research codebase built with friends :)

Transformer related optimization, including BERT, GPT

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

🐍 Geometric Computer Vision Library for Spatial AI

Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models

A prize for finding tasks that cause large language models to show inverse scaling

程序员延寿指南 | A programmer's guide to live longer

Programmer's guide about how to cook at home.

A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)

Soft Contextual Data Augmentation