kaballas's repositories
augmentoolkit
Convert Compute And Books Into Instruct-Tuning Datasets
AutoGPT
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.
BinaryVectorDB
Efficient vector database for hundred millions of embeddings.
chartify
Python library that makes it easy for data scientists to create charts.
chess_llm_interpretability
Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and representation of player Elo.
dspy
DSPy: The framework for programming—not prompting—foundation models
graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
lila-websocket
Experimental WebSocket server for lichess.org - superceded by https://github.com/ornicar/lila-ws
local-gemma
Gemma 2 optimized for your local machine.
LongLM
[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
rags
Build ChatGPT over your data, all with natural language
vsaq
VSAQ is an interactive questionnaire application to assess the security programs of third parties.
groqbook
Groqbook: Generate entire books in seconds using Groq and Llama3
llm.c
LLM training in simple, raw C/CUDA
mem0
The memory layer for Personalized AI
micrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
minbpe
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
MInference
To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.
Minitron
A family of compressed models obtained via pruning and knowledge distillation
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
RAGatouille
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
Samba
Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"
SmallLanguageModel-project
a LLM cookbook, for building your own from scratch, all the way from gathering data to training a model
storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Tricycle
Autograd to GPT-2 completely from scratch