kir-gadjello

zipslicer

A library for incremental loading of large PyTorch checkpoints

picoagent-rnd

Web & CLI capable LLM agent (research prototype, no framework dependencies).

extract_prompt

prompt reverse engineering for anyone, completely locally, on a cpu

safer_unpickle

GPICL

A replication of General-Purpose In-Context Learning by Meta-Learning Transformers https://arxiv.org/abs/2212.04458

kir-gadjello.github.io

my personal blog

llm

a cli tool to make local & remote LLMs useful in the shell (bonus: streaming & interactivity supported)

mpa-eval

A very quick benchmark sensitive to quantization of advanced LLMs

ChatGPT-Paper-Reader

This repo offers a simple interface that helps you to read&summerize research papers in pdf format. You can ask some questions after reading. This interface is developed based on openai API and using GPT-3.5-turbo model.

clipgrep

A semantic image search tool bringing venerable grep into a new AI era. Search by Prompt!

infinity

Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.

llama.cpp-oaicompat

Port of Facebook's LLaMA model in C/C++

MemGPT

Building persistent LLM agents with long-term memory 📚🦙

notes

Note-taking application, write down your thoughts.

palace-of-memories

personal memory spatial association environment

HandheldHelper

A personal fully local LLM client with builtin inference engine. Desktop & mobile support. GPLv3-licensed.

HungarianMathEval

An implementation of fully-automatic eval & grading for Hungarian high school math eval for LLMs

llamacpp-embed

A customized llama.cpp inference runtime I use for my desktop and mobile apps

llm_fns

Ultra-minimalistic unobtrusive functional LLM API abstractions

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level MLLM on Your Phone

obsidian-omnisearch

A personal fork of omniserch, a search engine that "just works" for Obsidian.

reflex-chat

A ChatGPT clone built in Reflex

RepoDreamer

A synthetic data generation engine for teaching LLMs project-level software engineering skills

SillyTavern

LLM Frontend for Power Users.

tabbyAPI

An OAI compatible exllamav2 API that's both lightweight and fast

text-embeddings-inference

A blazing fast inference solution for text embeddings models

vlcn-docs

vlcd docs site

WorkBench

WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting.