WatchGPT2

YOLOv5 ? in PyTorch > ONNX > CoreML > TFLite

Visualizer for neural network, deep learning and machine learning models

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

AI Code Completions

This repository contains demos I made with the Transformers library by HuggingFace.

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

Run Stable Diffusion on Mac natively

Chinese version of GPT2 training code, using BERT tokenizer.