Projects motion of pixels to a voxel

Entropy Based Sampling and Parallel CoT Decoding

Things you can do with the token embeddings of an LLM

A new chunking strategy developed by ZeroEntropy for general semantic chunking using Llama-70B.

Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead

supporting pytorch FSDP for optimizers

Seamlessly integrate LLMs as Python functions

The best repository showing why transformers might not be the answer for time series forecasting and showcasing the best SOTA non transformer models.

Site infrastructure for gwern.net. Custom Hakyll website with unique link archiving, popup UX, transclusions/collapses, dark+reader mode, bidirectional backlinks, and typography (sidenotes, dropcap…

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

Agents made simple - fit/predict pattern, JSON driven flows, and built in concurency support.

A Conversational Speech Generation Model

Memory-Bounded GPU Acceleration for Vector Search

Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"

Code for BLT research paper

A fully functional LLM chat backend with FastAPI and Async operations, with a built in MCTS conversation analyzer

This repository contains an exhaustive coverage of a hands on approach to PyTorch along side powerful tools to accelerate model tuning and training

R MCP Server

fully local, temporally aware natural language file search on your pc! even without a GPU. find relevant files using natural language in less than 1 second.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Using the moondream VLM with optical flow for promptable object tracking

Projects based on SigLIP (Zhai et. al, 2023) and Hugging Face transformers integration 🤗

small auto-grad engine inspired from Karpathy's micrograd and PyTorch

A neural audio search/retrieval library