Returns old TweetDeck, for free!

Utilities for PyTorch distributed

A set of Python scripts that makes your experience on TPU better

Bring portraits to life!

INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model

Multi-GPU CUDA stress test

Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI

Evaluating LLMs with Dynamic Data

LLM training in simple, raw C/CUDA

Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch

A simple to use pytorch wrapper for contrastive self-supervised learning on any neural network

Implementation of the transformer proposed in "Building Blocks for a Complex-Valued Transformer Architecture"

Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch

Simple Docker Compose NAS featuring Sonarr, Radarr, Prowlarr, Jellyfin, qBittorrent, PIA VPN and Traefik with SSL support

cython hooks for hatch

Golang plugin system over RPC.

Super simple MLX (apple silicon) CLIP based photo similarity web app

MTEB: Massive Text Embedding Benchmark

GGUF Swiss Army Knife

MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user develop their prompts into full models.

Manage a user environment using Nix [maintainer=@rycee]

Local CLIP search over meme libraries

eBPF-based autoinstrumentation of web applications and network metrics

training autoregressive transformers

PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)

CLOOB Conditioned Latent Diffusion training and inference code

CLOOB training (JAX) and inference (JAX and PyTorch)