Abacus.AI

Long-Context

This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and benchmark tasks that evaluate a model’s information retrieval capabilities with context expansion. We also include key experimental results and instructions for reproducing and building on them.

xai-bench

XAI-Bench is a library for benchmarking feature attribution explainability techniques

ForecastPFN

smaug

intraprocessing_debiasing

Code to accompany NeurIPS paper https://arxiv.org/abs/2006.08564

api-python

gh200-llm

Packages and instructions for training and inference of LLMs on NVIDIA's new GH200 machines

notebooks

Use Case Notebooks

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

to-the-cutoff

detect-pretrain-code-contamination

run tests in https://swj0419.github.io/detect-pretrain.github.io/ for contamination

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

xformers

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

min-tfs-client

A lightweight python gRPC client to communicate with TensorFlow Serving

streaming-javascript

transformers-bloom-inference

Fast Inference Solutions for BLOOM

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Puzzle-Generator-and-Solver

Puzzle Generator; Einstein's Riddle, Zebra Puzzle and Blood Donation Puzzle Solver. For non-commercial use only!

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs