ReFT: Representation Finetuning for Language Models

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Examples and guides for using the Gemini API

Python AI assistant 🧠

A natural language interface for computers

Master programming by recreating your favorite technologies from scratch.

Voice Assistant based on Whisper ASR and ChatGPT API

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

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

A Python implementation of the Kochawave fractal

An unofficial PyTorch implementation of the audio LM VALL-E

This repo includes ChatGPT prompt curation to use ChatGPT better.

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

OpenMMLab Text Detection, Recognition and Understanding Toolbox

generate granular word-level captions in srt format

In this repository, I will share some useful notes and references about deploying deep learning-based models in production.

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Pseudo API for Google Trends

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

Allows you easily scan for and delete scam comments using several methods.

Data augmentation for NLP

Pool-based active learning in Python

A modular active learning framework for Python

Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world application of a neural net trained with backpropagation.

Robust, Realtime, On-Device Face Liveness Detection (Face Anti Spoofing) Android

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

A peek into the tech and design at Lyst