cckuailong

search_with_lepton

Building a quick conversation-based search demo with Lepton AI.

Palworld-Reverse-Note

Palworld SAVE Reverse Note / 幻兽帕鲁逆向笔记

cvemap

Navigate the CVE jungle with ease.

magicoder

Magicoder: Source Code Is All You Need

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

scepter

SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.

Chinese-Mixtral-8x7B

中文Mixtral-8x7B（Chinese-Mixtral-8x7B）

unity-AI-Chat-Toolkit

使用unity实现AI聊天相关功能。目前这个库包含了对chatgpt、chatglm等大语言模型的api调用的代码实现以及实现了微软Azure以及百度AI的语音服务功能，语音服务均采用web api实现，支持Windows/WebGL/Android等平台

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

BELLE

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

DDColor

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

PhotoMaker

PhotoMaker

phpbb

phpBB Development: phpBB is a popular open-source bulletin board written in PHP. This repository also contains the history of version 2.

discourse

A platform for community discussion. Free, open, simple.

flarum

Simple forum software for building great communities.

surya

OCR, layout analysis, reading order, line detection in 90+ languages

mlx-examples

Examples in the MLX framework

Telechat

DB-GPT

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

OpenVoice

Instant voice cloning by MyShell.

MathPile

Generative AI for Math: MathPile

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

KwaiAgents

A generalized information-seeking agent system with Large Language Models (LLMs).

Emu

Emu Series: Generative Multimodal Models from BAAI

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

wails

Create beautiful applications using Go

StreamDiffusion

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

Multi-Modality-Arena

Chatbot Arena meets multi-modality! Multi-Modality Arena allows you to benchmark vision-language models side-by-side while providing images as inputs. Supports MiniGPT-4, LLaMA-Adapter V2, LLaVA, BLIP-2, and many more!