Training Sparse Autoencoders on Language Models

LCA-on-the-line (ICML 2024 Oral)

[NeurIPS 2024] How do Large Language Models Handle Multilingualism?

Official Implementation of weights2weights

This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."

Official PyTorch Implementation of "Rosetta Neurons: Mining the Common Units in a Model Zoo"

Official repo for paper DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

OS-ATLAS: A Foundation Action Model For Generalist GUI Agents

Out-of-the-box (OOTB) GUI Agent for Windows and macOS

具身智能入门指南

A generative world for general-purpose robotics & embodied AI learning.

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch

Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch

visualizing attention for LLM users

Visualizing the attention of vision-language models

Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, Inter…

[ECCV 2024 Oral] Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

Multi-Layer Sparse Autoencoders

Sparse autoencoders

Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.