Publiczne ślady GitHub EleutherAI

A framework for few-shot evaluation of language models.

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

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

Brak opisu dla tego repozytorium.

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

Sparsify transformers with SAEs and transcoders

Polyglot: Large Language Models of Well-balanced Competence in Multi-languages

Brak opisu dla tego repozytorium.

Erasing concepts from neural representations with provable guarantees

Keeping language models honest by directly eliciting knowledge encoded in their activations.

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

OSLO: Open Source for Large-scale Optimization

Official repository for the paper: Scaling Self-Supervised Representation Learning for Symbolic Piano Performance (ISMIR 2025)

Data processing system for polyglot

Experiments for efforts to train a new and improved t5

Minetest is an open source voxel game engine with easy modding and game creation

Efficient and robust implementation of seq-to-seq automatic piano transcription.

Mapping out the "memory" of neural nets with data attribution

One stop shop for all things carp

Brak opisu dla tego repozytorium.

Understanding how features learned by neural networks evolve throughout training

Brak opisu dla tego repozytorium.

Engineering the state of RNN language models (Mamba, RWKV, etc.)

Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from easy questions to hard

Brak opisu dla tego repozytorium.

Efficiently computing & storing token n-grams from large corpora

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

data related codebase for polyglot project

Pile Deduplication Code

Latent video diffusion

NeMo: a toolkit for conversational AI

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Closed-form polynomial approximations to neural networks

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Experiments in transformer knowledge and reasoning

Brak opisu dla tego repozytorium.

Linear probes with attention weighting

Equinox implementation of llama3 and llama3.1

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

Baseline agents for Minetest tasks.

MIDI tokenizers and pre-processing utils.

A library for mechanistic anomaly detection

Brak opisu dla tego repozytorium.

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Jupyter notebook for the interpretablity section of the minetester blog post

Data collection pipeline for CodeCARP. Includes PyCharm plugins.

Brak opisu dla tego repozytorium.

Adds GaLore style projection wrappers to optax optimizers

Repository to host architecture experiments and development using Paxml and Praxis

Brak opisu dla tego repozytorium.

yes

The code used in "Balancing Label Quantity and Quality for Scalable Elicitation"

Brak opisu dla tego repozytorium.

Robust recipes for to align language models with human and AI preferences

Project Repo for Unpaired Image Generation project

Brak opisu dla tego repozytorium.

Acompanying code for our research on SAE feature overlap when trained on different seeds.

Studying the variance in neural net predictions across training time

A replication of "EvilModel 2.0: Bringing Neural Network Models into Malware Attacks"

Library of interesting prompt generations

Can interpretability methods confer an advantage in competitive games?

Analogue of fMRI on artificial neural networks

https://github.com/xiexi51/RTopK PyTorch wrapper

Brak opisu dla tego repozytorium.

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

Brak opisu dla tego repozytorium.

A large instruct dataset for open-source models (WIP).

Mosaicml example benchmarks + LLM scripts

Minetest Game - The default game for the Minetest engine [https://github.com/minetest/minetest/]

Brak opisu dla tego repozytorium.

Investigating goal instability in RL

Democratizing Reinforcement Learning for LLMs

Exactly what it says on the tin

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Applying LEACE to models during training

GGML implementation of https://github.com/EleutherAI/aria

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

A simple, performant and scalable Jax LLM!

Minetest's fork of Irrlicht

App for generating html table from LM evaluation JSONs

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

Simplified library for mapping out the "memory" of neural nets with data attribution

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

Verifiers for LLM Reinforcement Learning

WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.

Ongoing research training transformer models at scale

Brak opisu dla tego repozytorium.

Brak opisu dla tego repozytorium.

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

implmentation of Plenoxels radiance fields without neural networks, with free nerf strategy

OSLO: Open Source for Large-scale Optimization

Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)

[WIP] a version of CLU with WandB logging added.

Compute FID scores with PyTorch.