Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

LLM101n: Let's build a Storyteller

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

An open-source tool-augmented conversational language model from Fudan University

A terminal workspace with batteries included

llama3.cuda is a pure C/CUDA implementation for Llama 3 model.

LLM training in simple, raw C/CUDA

This repository contains a LLM benchmark for the social deduction game `Resistance Avalon'

A fast, local neural text to speech system

A local chatbot fine-tuned by bilibili user comments.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Turns CSS blocks into style attributes

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gan…

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

LightGBM Rust library

Demangle Rust symbols

LLRT (Low Latency Runtime) is an experimental, lightweight JavaScript runtime designed to address the growing demand for fast and efficient Serverless applications.

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.

Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.

Bypass Paywalls web browser extension for Chrome and Firefox.

Super simple build framework with fast, repeatable builds and an instantly familiar syntax – like Dockerfile and Makefile had a baby.

为键盘工作者设计的单词记忆与英语肌肉记忆锻炼软件 / Words learning and English muscle memory training software designed for keyboard workers

Statsmodels: statistical modeling and econometrics in Python

🐎 Benchmarks for Inter-Process-Communication Techniques

A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports comp…

Zero-copy deserialization framework for Rust

Rust library for concurrent data access, using memory-mapped files, zero-copy deserialization, and wait-free synchronization.

nostr client to Exit Toxic Internet