Convolutional Neural Networks

build-once run-anywhere c library

Inference Llama 2 in one file of pure C

Open-source vector similarity search for Postgres

Wazuh - The Open Source Security Platform. Unified XDR and SIEM protection for endpoints and cloud workloads.

Locally run an Instruction-Tuned Chat-Style LLM

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

A vector search SQLite extension that runs anywhere!

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

Retro Games in Gym

Writing an OS in 1,000 lines.

Spike, a RISC-V ISA Simulator

✨Fast Coreference Resolution in spaCy with Neural Networks

mupdf mirror

Python bindings for the Transformer models implemented in C/C++ using GGML library.

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

An 8-bit minicomputer with a fully custom architecture

RISC-V Open Source Supervisor Binary Interface

C++ implementation for BLOOM

Universal Python binding for the LMDB 'Lightning' Database

Charm: A Framework for Rapidly Prototyping Cryptosystems

Source code for the 10th edition of Operating System Concepts

Locally run an Assistant-Tuned Chat-Style LLM

Multi-Threaded FP32 Matrix Multiplication on x86 CPUs

The project page for "LOGIC-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning"

Extension of the original word2vec using different architectures

Rank-based Unsupervised Keyword Extraction via Metavertex Aggregation