Adalberto

little-book-rl. The Little Book of Reinforcement Learning

VibeThinker. Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

goat. Generalized Optimal Transport Attention with Trainable Priors

TradingAgents. TradingAgents: Multi-Agents LLM Financial Trading Framework

database-CEPS. Este repositório contém informações detalhadas sobre os CEPs de todas as cidades do Brasil que estão cadastradas nos Correios.

ANE. Training neural networks on Apple Neural Engine via reverse-engineered private APIs

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

resume-template. The best LaTeX resume template.

AReaL. The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Open-DiffusionGS. Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction (ICCV 2025)

dllm. dLLM: Simple Diffusion Language Modeling

alphageometry. Python

opensloth. Python

duo. [ICML 2025] The Diffusion Duality

DreamOn. Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas

oconfronto. Medieval Browser RPG game made with vanilla PHP

min-max-gpt. Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training

mdlm. [NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

ManimML. ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

distilabel. Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

langflow. Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

diffusion-4k. [CVPR 2025] Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

ReDi. [NeurIPS'25 Spotlight] Boosting Generative Image Modeling via Joint Image-Feature Synthesis

flowseq. An official pytorch implementation of EACL2024 short paper "Flow Matching for Conditional Text Generation in a Few Sampling Steps"

SimpleAR. Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"

Dream. Dream 7B, a large diffusion language model

semanticist. (ICCV 2025) "Principal Components" Enable A New Language of Images

latent-gemma. Jupyter Notebook

imm. Official implementation of Inductive Moment Matching

RDLM. Official Code Repository for the paper "Continuous Diffusion Model for Language Modeling" (NeurIPS 2025).

nano-mdm. Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun

CrossFlow. [CVPR2025] PyTorch-based reimplementation of CrossFlow, as proposed in 'Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution'

native-sparse-attention-pytorch. Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper

Liger-Kernel. Efficient Triton Kernels for LLM Training

micro_diffusion. Official repository for our work on micro-budget training of large-scale diffusion models.

llama-box. LM inference server implementation based on *.cpp.

catvton-flux. Python

torchtune. PyTorch native post-training library

SO-ARM100. Standard Open Arm 100

InstantMesh. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

OpenLRM. An open-source impl. of Large Reconstruction Models

LP-3DGS. C++

splatt3r. Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

ComfyUI-Fluxtapoz. Nodes for image juxtaposition for Flux in ComfyUI

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

nGPT-pytorch. Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI

mini-omni. open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

stable-diffusion.cpp. Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

fish-speech. SOTA Open Source TTS

MVDream. Multi-view Diffusion for 3D Generation

MVDream-threestudio. 3D generation code for MVDream

transformers_zamba2. Python

Zamba2. PyTorch implementation of models from the Zamba2 series.

DistillKit. An Open Source Toolkit For LLM Distillation

NeuralFlow. Visualize the intermediate output of Mistral 7B

framed-multi30k. Jupyter Notebook

ChunkLlama. [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

Glyph-ByT5. [ECCV2024] This is an official inference code of the paper "Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering" and "Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering""

mamba2-torch. Python

matmulfreellm. Implementation for MatMul-free LM.

RETRO-pytorch. Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

neuron_as_deep_net. Code behind the work "Single Cortical Neurons as Deep Artificial Neural Networks", published in Neuron 2021

minRF. Minimal implementation of scalable rectified flow transformers, based on SD3's approach

awesome-kan. A comprehensive collection of KAN(Kolmogorov-Arnold Network)-related resources, including libraries, projects, tutorials, papers, and more, for researchers and developers in the Kolmogorov-Arnold Network field.

fast-kan. FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)

gym-chess. A simple chess environment for openai/gym

efficient-kan. An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

FourierKAN. Python

pykan. Kolmogorov Arnold Networks

outlines. Structured Outputs

infini-transformer. PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)

spacebyte. A byte-level decoder architecture that matches the performance of tokenized Transformers.

InfiniTransformer. Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

AutoCompressors. [EMNLP 2023] Adapting Language Models to Compress Long Contexts

attorch. A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

llama-cpp-python. Python bindings for llama.cpp

LLMLingua. [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

conditional-flow-matching. TorchCFM: a Conditional Flow Matching library

flow-matching. Annotated Flow Matching paper

BitMat. An efficent implementation of the method proposed in "The Era of 1-bit LLMs"

smaller-transformers. Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

1.58BitNet. Experimental BitNet Implementation

Triton-Puzzles. Puzzles for learning Triton

quiet-star. Code for Quiet-STaR

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

BitNet. Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

needle-in-a-haystack. Doing simple retrieval from LLM models at various context lengths to measure accuracy

SimpleBitNet. Simple Adaptation of BitNet

GaLore. GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

rebased. Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"

based. Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"

axolotl. Go ahead and axolotl questions

DRUGS. Stop messing around with finicky sampling parameters and just use DRµGS!

TOVA. Token Omission Via Attention

laserRMT. This is our own implementation of 'Layer Selective Rank Reduction'

llm-autoeval. Automatically evaluate your LLMs in Google Colab

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.

bovespaStockRatings. Crawler for Fundamental analysis platform for BOVESPA stocks, generating a score for each share according to the selected criteria on the indicators.

PowerInfer. High-speed Large Language Model Serving for Local Deployment

Pallaidium. PALLAIDIUM — a generative AI movie studio, seamlessly integrated into the Blender Video Editor (VSE), enabling end-to-end production from script to screen and back.

pause-transformer. Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount of time on any token

minimal-text-diffusion. A minimal implementation of diffusion models for text generation

openWakeWord. An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

RealtimeSTT. A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

wanda. A simple and effective LLM pruning approach.

lm-evaluation-harness. A framework for few-shot evaluation of language models.

test. Measuring Massive Multitask Language Understanding | ICLR 2021

instruct-eval. This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

LLM-Pruner. [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

DoLa. Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

dream-textures. Stable Diffusion built-in to Blender

CoDeF. [CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

hugging-chat-api. HuggingChat Python API🤗

candle. Minimalist ML framework for Rust

llama2.rs. A fast llama2 decoder in pure Rust.

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

softmax_variants. PyTorch code for softmax variants: center loss, cosface loss, large-margin gaussian mixture, COCOLoss, ring loss

MeZO. [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

Sophia. The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”

gptq. Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

CodeCapybara. Open-source Self-Instruction Tuning Code LLM

DeepFakeTorch. Python

StableLM. StableLM: Stability AI Language Models

RWKV-LM. RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

RRHF. [NIPS2023] RRHF & Wombat

EditAnything. Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

SD-CN-Animation. This script allows to automate video stylization task using StableDiffusion and ControlNet.

tomesd. Speed up Stable Diffusion with this one simple trick!

Text2Video-Zero. [ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

align_sd. Better Aligning Text-to-Image Models with Human Preference. ICCV 2023

modern-srwm. Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep RL Workshop) and "Accelerating Neural Self-Improvement via Bootstrapping" (ICLR 2023 Workshop)

modelscope. ModelScope: bring the notion of Model-as-a-Service to life.

alpaca-lora. Instruct-tune LLaMA on consumer hardware

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

ggml. Tensor library for machine learning

gigagan-pytorch. Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

qdrant-client. Python client for Qdrant vector search engine

qdrant. Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

SpikeGPT. Implementation of "SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks"

torchscale. Foundation Architecture for (M)LLMs

denoising-diffusion-gan. Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

automl. Google Brain AutoML

Universal-Guided-Diffusion. Jupyter Notebook

ControlNet. Let us control diffusion models!

whisper.cpp. Port of OpenAI's Whisper model in C/C++

language-model-agents. Experiments with generating opensource language model assistants

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

kernl. Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

GLM-130B. GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

instruct-pix2pix. Python

sd-leap-booster. Fast finetuning using a booster model that puts the initial state to a local minimum

muse-maskgit-pytorch. Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

reward-modeling. Python

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

Structured-Diffusion-Guidance. Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

CfC. Closed-form Continuous-time Neural Networks

CrossAttentionControl. Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion

stablediffusion-infinity. Outpainting with Stable Diffusion on an infinite canvas

stable-diffusion. Jupyter Notebook

unified-io-inference. Jupyter Notebook

stable-diffusion-webui. Stable Diffusion web UI

waifu-diffusion. stable diffusion finetuned on weeb stuff

dpm-solver. Official code for "DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps" (Neurips 2022 Oral)

stable-diffusion. Optimized Stable Diffusion modified to run on lower GPU VRAM

diffusers-interpret. Diffusers-Interpret 🤗🧨🕵️‍♀️: Model explainability for 🤗 Diffusers. Get explanations for your generated images.

glid-3-xl-stable. stable diffusion training

stable-diffusion. A latent text-to-image diffusion model

Palette-Image-to-Image-Diffusion-Models. Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

CEIA-ProjetoImaginie. Repositório dos códigos desenvolvidos no projeto Algoritmos Inteligentes para captação e retenção de usuários em plataformas educacionais.

darts. A python library for user-friendly forecasting and anomaly detection on time series.

convert-labse-tf-pt. Convert LaBSE model from TF Hub to PyTorch.

smaller-labse. Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE

GFPGAN. GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

YourTTS. YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

blitz-bayesian-deep-learning. A simple and extensible library to create Bayesian Neural Network layers on PyTorch.

pytorch-spiking. Spiking neuron integration for PyTorch

notebooks. Notebooks using the Hugging Face libraries 🤗

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

server-express-typescript-template. JavaScript

react-template. TypeScript

previsao-do-tempo. Site de previsão do tempo construído para demonstrar conhecimentos em Typescript, React, Redux, Python e Docker

Cirq. Python framework for creating, editing, and running Noisy Intermediate-Scale Quantum (NISQ) circuits.