ivannz

typos

Source code spell checker

CVE-2024-1086

Universal local privilege escalation Proof-of-Concept exploit for CVE-2024-1086, working on most Linux kernels between v5.14 and v6.6, including Debian, Ubuntu, and KernelCTF. The success rate is 99.4% in KernelCTF images.

ai-research-assistant

Aria is Your AI Research Assistant Powered by GPT Large Language Models

Recall2Imagine

Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024

extending-jax

Extending JAX with custom C++ and CUDA code

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

promptimize

Promptimize is a prompt engineering evaluation and testing toolkit.

pydata-global-2023-hpc

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

llama.cpp

LLM inference in C/C++

koboldcpp

A simple one-file way to run various GGML and GGUF models with KoboldAI's UI

LLM-Research

A collection of LLM related papers, thesis, tools, datasets, courses, open source models, benchmarks

alphageometry

DifferentiableSVD

A collection of differentiable SVD methods and ICCV21 "Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?"

uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

faiss

A library for efficient similarity search and clustering of dense vectors.

Hinglish-Translation-AI-llama2

Built an english to hinglish translator by fine-tunning Llama-2 LLM. The translated text sounds natural and also convert all the difficult words and phrases in English to Hinglish. The translated text is easy to understand for even a non-native Hindi speaker.

LLM-Agent-Paper-List

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

mlx

MLX: An array framework for Apple silicon

compositional-sculpting

Code for paper "Compositional Sculpting of Iterative Generative Processes"

dior

Differentiable reparameterization of matrices with orthogonal columns.

jax2numpy

movfuscator

The single instruction C compiler

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

scipy2023-deeplearning

statsforecast

Lightning ⚡️ fast forecasting with statistical and econometric models.

makemore

An autoregressive character-level language model for making more things

open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

langchain

🦜🔗 Build context-aware reasoning applications