proger

PINNs

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

graph-of-thoughts

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

Sketchbook

3D playground built on three.js and cannon.js.

schedule_free

Schedule-Free Optimization in PyTorch

Multi-Agent-Reinforcement-Learning-Environment

Hello, I pushed some python environments for Multi Agent Reinforcement Learning.

gymnax

RL Environments in JAX 🌍

jumanji

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

recurrentgemma

Open weights language model from Google DeepMind, based on Griffin.

speech-trident

Awesome speech/audio LLMs, representation learning, and codec models

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

weightnorm

Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks"

JaxMARL

Multi-Agent Reinforcement Learning with JAX

v6502r

visual6502 remixed

morton

video2game

Code release of Video2Game

d3pm

Minimal Implementation of a D3PM in pytorch

fastfit

FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes

llm-adaptive-attacks

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

weight_norm

Lasagne code for weight normalization

gsheets-connection

gptcore

Fast modular code to create and train cutting edge LLMs

LASP

Linear Attention Sequence Parallelism (LASP)

fregrad

Code repository for FreGrad

SmallInitEmb

LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence

torchcomp

Differentiable dynamic range controller in PyTorch.

HGRN2

HGRN2: Gated Linear RNNs with State Expansion

rnngineering

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

heinsen_attention

Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)

ctc-copy

[EMNLP'23] Code for "Non-autoregressive Text Editing with Copy-aware Latent Alignments".

LangToGroup

Implementation of Isoperimetric and Isodiametric Functions of Groups in Haskell