通义千问VLLM推理部署DEMO

FastGPT is a knowledge-based QA system built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization!

基于chatgpt-on-wechat框架，只能运行在Win平台的项目，通过本项目可以将微信或者企业微信个人号接入ChatGpt、文心一言、FastGpt、LinkAI，可以文字对话、语音对话、图片交互、文件交互等。

为ChatGPT/GLM提供实用化交互界面，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm2等本地模型。兼容文心一言, moss, llama2, rwkv, claude2, 通义千问, 书生, 讯飞星火等。

https://docs.byzer.org

Easy-to-use fine-tuning framework using PEFT (PT+SFT+RLHF with QLoRA) (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyp…

Tracking Ray Enhancement Proposals

中文nlp解决方案(大模型、数据、模型、训练、推理)

lzh_llm_finetune

Ray Aviary - evaluate multiple LLMs easily

A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, OPT, and GALACTICA.

Byzer (former MLSQL): A low-code open-source programming language for data pipeline, analytics and AI.

English SDK for Apache Spark

同济子豪兄的公开课

NebulaGraph DGL(Deep Graph Library) Integration Package. (WIP)

Model parallel transformers in JAX and Haiku

算法全栈之路

A distributed, fast open-source graph database featuring horizontal scalability and high availability

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.

Deep Learning System core principles introduction.

PyTorch Library for Fast and Easy Distributed Graph Learning

FUSE-based file system backed by Amazon S3

2021 MAXP 命题赛 任务一：基于DGL的图机器学习任务。队伍：Graph@ICT，🥉rank6。https://www.biendata.xyz/competition/maxp_dgl/

Ray tutorials from Anyscale