Customize your Zotero workflow.

Agentic components of the Llama Stack APIs

A minimal GPU design in Verilog to learn how GPUs work from the ground up

Run and customize Local LLMs.

a simple, low cost, robotics gripper

A PyTorch Native LLM Training Framework

Efficient Transformers with Dynamic Token Pooling

A pipeline to improve skills of large language models

Let's make sand talk

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

A project for training foundational Danish language model

Triton Implementation of HyperAttention Algorithm

A comprehensive deep dive into the world of tokens

What would you do with 1000 H100s...

Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU

A framework for few-shot evaluation of language models.

GPTQ inference Triton kernel

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Markovian State and Action Abstractions for MDPs via Hierarchical MCTS within a POMDP Formulation

Hierarchical Online Planning and Reinforcement Learning on Taxi

AI•ON projects repository and website source.

Learning a game engine by example.

Unsupervised learning of visual concepts from video

Persistent advantage learning dueling double DQN for the Arcade Learning Environment