Thytu

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

llamafile

Distribute and run LLMs with a single file.

guidance

A guidance language for controlling large language models.

prophet

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

gum

A tool for glamorous shell scripts 🎀

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

primitive

Reproducing images with geometric primitives.

gorilla

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

triton

Development repository for the Triton language and compiler

Gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

axolotl

Go ahead and axolotl questions

lm-evaluation-harness

A framework for few-shot evaluation of language models.

clearml

ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

DALI

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

mergekit

Tools for merging pretrained large language models.

PettingZoo

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

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.

TabPFN

Official implementation of the TabPFN paper (https://arxiv.org/abs/2207.01848) and the tabpfn package.

Video-Encode

Encodes a file into a video format to store on a cloud video hosting service

fastertransformer_backend

task_vectors

Editing Models with Task Arithmetic

pixel

Research code for pixel-based encoders of language (PIXEL)

Binder

[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"

clearml-serving

ClearML - Model-Serving Orchestration and Repository Solution

stockfish

Integrates the Stockfish chess engine with Python (Official fork)

PyTorchPartialLayerFreezing

A simple code snippet for freezing only part of the layer