DDanlov's starred repositories
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
hyperlight
Modular and intuitive Hypernetworks in Pytorch
ShiftAddLLM
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
self-reasoning-tokens-pytorch
Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto
LLM_Tree_Search
(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training
CALM-pytorch
Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind
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
annotated_deep_learning_paper_implementations
๐งโ๐ซ 60 Implementations/tutorials of deep learning papers with side-by-side notes ๐; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), ๐ฎ reinforcement learning (ppo, dqn), capsnet, distillation, ... ๐ง
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
Qwen-Audio
The official repo of Qwen-Audio (้ไนๅ้ฎ-Audio) chat & pretrained large audio language model proposed by Alibaba Cloud.
mirasol-pytorch
Implementation of ๐ป Mirasol, SOTA Multimodal Autoregressive model out of Google Deepmind, in Pytorch
Perceiver-Music-Transformer
SOTA Google's Perceiver-AR Music Transformer Implementation and Model