Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State

A library for mechanistic interpretability of GPT-style language models

Locating and editing factual associations in GPT (NeurIPS 2022)

Find context neurons in Pythia models.

Sparse probing paper full code.

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…

Code for paper "Multiple Physics Pretraining for Physical Surrogate Models

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

Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.

Demo code for the paper -- Spatial interpolation using conditional generative adversarial neural networks

Tools for understanding how transformer predictions are built layer-by-layer

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

The Python programming language

The official Meta Llama 3 GitHub site

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

awesome papers in LLM interpretability

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

Tensors and Dynamic neural networks in Python with strong GPU acceleration

PyTorch code and models for V-JEPA self-supervised learning from video.

Inference code for Llama models

The official PyTorch implementation of Google's Gemma models