Skip to content

Latest commit

 

History

History
67 lines (62 loc) · 4 KB

library.org

File metadata and controls

67 lines (62 loc) · 4 KB

Library

Different from language libraries, here lists some generic frameworks, that are exposed to many languages by ffi.

Or they are focused on CS fields instead of language itself, such as most of AI projects are in python but they are topic on AI instead of python.

Compression

zstd
Zstandard - Fast real-time compression algorithm

Graphics

Library

openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Project

waifu2x
Image Super-Resolution for Anime-style art using Deep Convolutional Neural Networks. And it supports photo.

Tutor

learnopengl

Artificial Intelligence

Machine Learning

LLM

Some Productions

serge
a chat interface crafted with llama.cpp for running Alpaca models. No API keys, entirely self-hosted!
petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
text generation webui
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, llama.cpp (GGUF), Llama models.

Dev Framework

langchain
chain prompt, llm, and other actions togather such as agent
griptape
like langchain, but different architecture
langserve
langflow
Langflow is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.
fastchat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena. Webui, controller, model (worker) API architecture.
autogpt
an experimental open-source application showcasing the capabilities of the GPT-4 language model. It is used for agent development.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs. It supports OpenAI api and self designed api for models.
MetaGPT
The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
gpt-polit
Dev tool that writes scalable apps from scratch while the developer oversees the implementation.

train/model/datasets

awesome llm human perference datasets
a collection of human preference datasets for LLM instruction tuning, RLHF and evaluation.
huggingface
The AI community building the future.
hf-mirror
huggingface mirror
colossal ai
Making large AI models cheaper, faster and more accessible
LLaMA
A foundational, 65-billion-parameter large language model. Made by Meta.Inc.
redpajama
An Open Source Recipe to Reproduce LLaMA training dataset
dolly
the first open source, instruction-following LLM, fine-tuned on a human-generated instruction dataset licensed for research and commercial use.

awesome

awesome-llm