qingmingsang

ebsynth_utility

AUTOMATIC1111 UI extension for creating videos using img2img and ebsynth.

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

driver.js

A light-weight, no-dependency, vanilla JavaScript engine to drive the user's focus across the page

bloop

bloop is a fast code search engine written in Rust.

pdfGPT

PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!

Webpilot

gl-matrix

Javascript Matrix and Vector library for High Performance WebGL apps

glTF

glTF – Runtime 3D Asset Delivery

spine-runtimes

2D skeletal animation runtimes for Spine.

monaco-editor

A browser based code editor

color-fns

color functions for node and browser

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

ColossalAI

Making large AI models cheaper, faster and more accessible

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

llama

Inference code for Llama models

paper-reading

深度学习经典、新论文逐段精读

CodeGeeX2

CodeGeeX2: A More Powerful Multilingual Code Generation Model

starcoder

Home of StarCoder: fine-tuning & inference!

tree-sitter

An incremental parsing system for programming tools

GLM-130B

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

metaseq

Repo for external large-scale work

Flowise

Drag & drop UI to build your customized LLM flow

langflow

⛓️ Langflow is a visual framework for building multi-agent and RAG applications. It's open-source, Python-powered, fully customizable, model and vector store agnostic.

CodeGeeX

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

llama_index

LlamaIndex is a data framework for your LLM applications

web-llm

High-performance In-browser LLM Inference Engine

llama.cpp

LLM inference in C/C++

langchainjs

🦜🔗 Build context-aware reasoning applications 🦜🔗

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

ChatGLM-Efficient-Tuning

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调