nat

llama.cpp

LLM inference in C/C++

chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

langflow

⛓️ Langflow is a dynamic graph where each node is an executable unit. Its modular and interactive design fosters rapid experimentation and prototyping, pushing hard on the limits of creativity.

fauxpilot

FauxPilot - an open-source alternative to GitHub Copilot server

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

LaTeX-OCR

pix2tex: Using a ViT to convert images of equations into LaTeX code.

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

ChatRWKV

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

aider

aider is AI pair programming in your terminal

FasterTransformer

Transformer related optimization, including BERT, GPT

CodeGen

CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

WebGPT

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

mctx

Monte Carlo tree search in JAX

cbp-translate

tier

The easiest way to add pricing to your SaaS. Get billing over with.

gpt-commit-summarizer

samsung-frame-art

A small script that makes it easy to fling a folder of images onto the Samsung Frame TV

elk

Keeping language models honest by directly eliciting knowledge encoded in their activations.

yfs

Synchronize text files between browser and disk using Yjs and the File System Access API

Vesuvius-First-Letters

embedland

A collection of text embedding experiments

scroll-viewer

thingies

Various little scripts I use.

VolumeAnnotate

Virtual Unwrapping Tool for the Vesuvius Challenge

khartes

vesuvius-blender

Crackle-Viewer

Vesuvius Challenge Ink Crackle Labeling Tool for Scroll Segmentations