T5 onnxruntime cpp

Compressed LLMs for Efficient Text Generation [ICLR'24 Workshop]

Question answering system for PDF files

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

A library & tools to evaluate predictive language models.

📝 A text file containing 479k English words for all your dictionary/word-based projects e.g: auto-completion / autosuggestion

Rust libraries and programs focused on succinct data structures

Modern spell checking library - accurate, fast, multi-language

Tutorial for Porting PyTorch Transformer Models to Candle (Rust)

SCOWL (and friends).

Typo Detector using Transformers ⚡. Demo (👇 )

A modern C++ header only SQLite3 wrapper

SQLite3++ - C++ wrapper of SQLite3 API

MLX: An array framework for Apple silicon

This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone".

C++ project structure with Google Test (gtest) example using CMake as build system.

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

Transformer related optimization, including BERT, GPT

Typing Assistant provides the ability to autocomplete words and suggests predictions for the next word. This makes typing faster, more intelligent and reduces effort.

NeuSpell: A Neural Spelling Correction Toolkit

Prune a model while finetuning or training.

Group Fisher Pruning for Practical Network Compression(ICML2021)

Jupyter notebooks for the Natural Language Processing with Transformers book

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

Inference code for Llama models

Bolt is a deep learning library with high performance and heterogeneous flexibility.

Android Keyboard with 180+ dictionaries. Support swipe input (sliding input), Emoji keyboard, AI predictions, dictionaries downloading, and keyboard themes.

oneAPI Threading Building Blocks (oneTBB)

Universal LLM Deployment Engine with ML Compilation

A simple framework for mobile system design interviews