SpaCy 中文模型 | Models for SpaCy that support Chinese

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Network Analysis in Python

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

Implementation of "Attention Is Off By One" by Evan Miller

A high-throughput and memory-efficient inference and serving engine for LLMs

A terminal for a more modern age

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

The personal repository of the work: *DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer*.

A cross-version Python bytecode decompiler

A Markdown-based note-taking app for mobile devices.