shawnhowell Goto Github PK

glm-130b

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

gpt-4-llm

gpt2-chinese

Chinese version of GPT2 training code, using BERT tokenizer.

gptq-for-llama

4 bits quantization of LLaMA using GPTQ

habitlabmobile

An app that helps users keep track of time spent on their mobile device.

he4o

和（he for objective-c） —— “以螺旋论为基础开发的信息熵减机（通用人工智能系统）”

helix_theory

螺旋论（theory of helix）—— “熵减机理论（可用来构建AGI、复杂性系统等）”

kgqa_hlm

基于知识图谱的《红楼梦》人物关系可视化及问答系统

langtorch

Building composable LLM applications with Java / JVM.

lazyminer

The Lazyminer project, Non-Axiomatic Reasoning for rule mining on mobile devices.

lmflow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All.

malmo

Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:

malmomo

deep RL hacking on minecraft with malmo

megatron-lm

Ongoing research training transformer models at scale

multi-agent-emergence-environments

Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"

nebullvm

Plug and play modules to optimize the performances of your AI systems 🚀

nlp-roadmap

📚 机器学习、深度学习、自然语言处理学习路线图 及 AI方向学习资源、工具

non-axiomatic-reasoner

A Non-Axiomatic Inference System built on Holochain.

open-indoor-localization

And simple indoor localization app and script for new beginner to start. （中文链接见后）

open-llama

The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.

open_flamingo

An open-source framework for training large multimodal models.

openchatkit

palm-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

plan4mc

Reinforcement learning and planning for Minecraft.

pythia

resnetgpt

用Resnet101+GPT搭建一个玩王者荣耀的AI

roughnlp

A very simple NLP system for NARS, for beginners, based on some simple matching mechanisms.

sizzle

A sizzlin' hot selector engine.

smarper

SmarPer: Context-Aware and Automatic Runtime-Permissions for Mobile Devices

soargym

Interfacing the Soar cognitive architecture with OpenAI Gym