cbiehl

omegaconf

Flexible Python configuration system. The last one you will ever need.

safetensors

Simple, safe way to store and distribute tensors

tabzilla

carte

Repository for CARTE: Context-Aware Representation of Table Entries

ludwig

Low-code framework for building custom LLMs, neural networks, and other AI models

TabSurvey

Experiments on Tabular Data Models

be_great

A novel approach for synthesizing tabular data using pretrained large language models

carbon

:black_heart: Create and share beautiful images of your source code

mistral-finetune

SMAC3

SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization

GPTFast

Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.

llm.c

LLM training in simple, raw C/CUDA

optuna

A hyperparameter optimization framework

pykan

Kolmogorov Arnold Networks

transtab

NeurIPS'22 | TransTab: Learning Transferable Tabular Transformers Across Tables

relbench

RelBench: Relational Deep Learning Benchmark

universal_pathlib

pathlib api extended to use fsspec backends

pytorch-frame

Tabular Deep Learning Library for PyTorch

Sophia

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

awslogs

AWS CloudWatch logs for Humans™

BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

codellama

Inference code for CodeLlama models

flaxformer

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

pathlibfs

pytorch-struct

Fast, general, and tested differentiable structured prediction in PyTorch

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

StableLM

StableLM: Stability AI Language Models