kaballas

AISECKG-QA-Dataset

app

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.

Autotrain

BinaryVectorDB

Efficient vector database for hundred millions of embeddings.

chartify

Python library that makes it easy for data scientists to create charts.

chess-position-embeddings

code for training and using chess embeddings models

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.

DiskVectorIndex

kaballas/DiskVectorIndex

kaballas/AISECKG-QA-Dataset

kaballas/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.

kaballas/chartify

Python library that makes it easy for data scientists to create charts.

kaballas/chess-position-embeddings

code for training and using chess embeddings models

kaballas/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.

kaballas/dspy

DSPy: The framework for programming—not prompting—foundation models

kaballas/graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

kaballas/local-gemma

Gemma 2 optimized for your local machine.

kaballas/groqbook

Groqbook: Generate entire books in seconds using Groq and Llama3

kaballas/llm.c

LLM training in simple, raw C/CUDA

kaballas/LongWriter

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

kaballas/mem0

The memory layer for Personalized AI

kaballas/micrograd

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

kaballas/minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

kaballas/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.

kaballas/Minitron

A family of compressed models obtained via pruning and knowledge distillation

kaballas/multi1

ol1-p1: Using Ollama or Perplexity to create o1-like reasoning chains

kaballas/nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

kaballas/nino

Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks"

kaballas/nvdlib

A simple wrapper for the National Vulnerability CVE/CPE API

kaballas/qtip

kaballas/RAG_Techniques

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.

kaballas/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.

kaballas/Samba

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

kaballas/SmallLanguageModel-project

a LLM cookbook, for building your own from scratch, all the way from gathering data to training a model

kaballas/storm

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

kaballas/train-student-gpt

Training a small language model from scratch on student lecture commentary

kaballas/Tricycle

Autograd to GPT-2 completely from scratch

kaballas/Zamba2

PyTorch implementation of models from the Zamba2 series.