DDanlov

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

video-occupancy-models

hyperlight

Modular and intuitive Hypernetworks in Pytorch

ShiftAddLLM

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

pam

pykan

Kolmogorov Arnold Networks

self-reasoning-tokens-pytorch

Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto

relu_kan

DIY-Astra

LLM_Tree_Search

(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training

init2winit

mad-lab

A MAD laboratory to improve AI architecture designs 🧪

grok-1

Grok open release

CALM-pytorch

Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind

OpenDiT

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

seq_icl

goodai-ltm-benchmark

A library for benchmarking the Long Term Memory and Continual learning capabilities of LLM based agents. With all the tests and code you need to evaluate your own agents. See more in the blogpost:

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

Pushdown-Layers

Code for Pushdown Layers from our EMNLP 2023 paper

dnc

A TensorFlow implementation of the Differentiable Neural Computer.

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

ponder-transformer

Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper

dataset-generator

A new way to generate large quantities of high quality synthetic data (on par with GPT-4), with better controllability, at a fraction of the cost of prompting LLMs directly.

neuralstruct

Differentiable data structures for neural nets

quip-sharp

QuIP

Qwen-Audio

The official repo of Qwen-Audio (通义千问-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.

mirasol-pytorch

Implementation of 🌻 Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch

DT_Mem

Thisi is the official code base for paper "Think Before You Act: Decision Transformers with Internal Working Memory"

Perceiver-Music-Transformer

SOTA Google's Perceiver-AR Music Transformer Implementation and Model