gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Trying to figure various CPU things out

Flexible I/O Tester

Repository for submission to the COLING GenAI Content Detection Shared Task 3: "Cross-domain Machine-Generated Text Detection"

A course of building an LSM-Tree storage engine (database) in a week.

Low-overhead tracing of all Linux kernel-user transitions, for serious performance analysis. Includes kernel patches, loadable module, and post-processing software. Output is HTML/SVG per-CPU-core …

Achieve arbitrary kernel read/writes/function calling in Hypervisor-Protected Code Integrity (HVCI) protected environments calling without admin permissions or kernel drivers.

LLM101n: Let's build a Storyteller

Companion code for FanOutQA: Multi-Hop, Multi-Document Question Answering for Large Language Models (ACL 2024)

Curated list of project-based tutorials

Collection of custom elements that appear hand drawn. Great for wireframes or a fun look.

RAID is the largest and most challenging benchmark for AI-generated text detection. (ACL 2024)

LLM training in simple, raw C/CUDA

Democratizing NLP!

Push-Button End-to-End Testing of Kubernetes Operators and Controllers

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

Kani extension for supporting vision-language models (VLMs). Comes with model-agnostic support for GPT-Vision and LLaVA.

Code for the INTERSPEECH 2023 paper "Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models"

Foundational Models for State-of-the-Art Speech and Text Translation

NLP Discord bot

CALYPSO is a LLM-powered Dungeon Master's assistant. Read "CALYPSO: LLMs as Dungeon Masters' Assistants" for more info.

Tensor library for machine learning

Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

Code for the AAAI 2023 Paper "Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated Text"

me doing leet code

Simple x86-64 VT-x Hypervisor with EPT Hooking

Simpleator ("Simple-ator") is an innovative Windows-centric x64 user-mode application emulator that leverages several new features that were added in Windows 10 Spring Update (1803), also called "R…

LLVM pass that detects one undefined behavior, and emits code to delete your hard drive