HP2706

Auto_HookPoint

instructor-rs

structured extraction for llms in rust

mechinterp-autoencoders

web-codegen

github copilot but on the browser.

1000-x

demo-bert

This is a BERT large language model starter template from Banana.dev that allows on-demand serverless GPU inference.

easy_typecheck

evolutionary-Simulation

image_from_audio

ImageBind

ImageBind One Embedding Space to Bind Them All

instructor

structured outputs for llms

ku_devops

llm-editor

megabyte

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

nextjs_streaming_bug

otfusion

Model Fusion via Optimal Transport, NeurIPS 2020

quantize_w_modal

ReplitLM

pruning replitLM with seeing is believing method

repo2prompt

Turn a Github Repo's contents into a big prompt for long-context models like Claude 3 Opus.

sparsegpt

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

typescript-demo-chess_game

web-embeddings

Embeddings based on webgpt on webgpu

writingWithLiveImages