lexiconium

pykan

Kolmogorov Arnold Networks

kanrl

Kolmogorov-Arnold Network for Reinforcement Leaning, initial experiments

bevy_rl

Reinforcement Learning environments with Bevy

openui

OpenUI let's you describe UI using your imagination, then see it rendered live.

llamafile

Distribute and run LLMs with a single file.

GaLore

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

professional-programming

A collection of learning resources for curious software engineers

triton

Development repository for the Triton language and compiler

magika

Detect file content types with deep learning

StableCascade

Official Code for Stable Cascade

gfn-lm-tuning

ML-Papers-of-the-Week

🔥Highlighting the top ML papers every week.

deep-language-networks

We view Large Language Models as stochastic language layers in a network, where the learnable parameters are the natural language prompts at each layer. We stack two such layers, feeding the output of one layer to the next. We call the stacked architecture a Deep Language Network - DLN

Stirling-PDF

#1 Locally hosted web application that allows you to perform various operations on PDF files

heynote

A dedicated scratchpad for developers

StreamDiffusion

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

rust-gpu

🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

AnimateDiff

Official implementation of AnimateDiff.

tdmpc2

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

rl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

candle

Minimalist ML framework for Rust

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

AFFiNE

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models