Beast code in Giters

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

Language:TypeScriptNOASSERTION3287100

llama3-Chinese-chat

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

Language:Python311100

elasticsearch-labs

Notebooks & Example Apps for Search & AI Applications with Elasticsearch

Language:Jupyter NotebookApache-2.044400

spring-ai

An Application Framework for AI Engineering

Language:JavaApache-2.0230300

WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Language:Python899700

ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.

Language:GoMIT7195200

markmap

Visualize markdown documents as mindmaps

Language:JavaScriptMIT165200

markmap

Build mindmaps with plain text

Language:TypeScriptMIT725100

GPTs

leaked prompts of GPTs

2693900

AIGC_Resources

Gather AIGC most useful tools, materials, publications and reports

11800

jsmind

a mind mapping library built by javascript

Language:JavaScriptNOASSERTION330200

grok-1

Grok open release

Language:PythonApache-2.04897100

TheBigPromptLibrary

A collection of prompts, system prompts and LLM instructions

Language:HTMLMIT53100

LM-from-scratch

LM from scratch

Language:Jupyter Notebook400

GPTS-Prompt-Collection

收集GPTS的prompt / Collect the prompt of GPTS

MIT98600

ai-hub

AI Hub 是一个为了接入包括ChatGPT、Baichuan、Zhipu、混元、MiniMax、Moonshot等多种大型语言模型而设计的服务。它旨在积累和管理各种有效的模型调用提示（prompt），并对这些大型语言模型进行持续的测试和评估。

Language:JavaApache-2.05200

hh-rlhf

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

MIT147100

spinningup

An educational resource to help anyone learn deep reinforcement learning.

Language:PythonMIT974100

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

Language:PythonMIT224500

GLM-130B

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

Language:PythonApache-2.0763100