huihuipiaomiao

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

ArxivPapers

Code behind Arxiv Papers

sglang

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

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

Scrapegraph-ai

Python scraper based on AI

llama_index

LlamaIndex is a data framework for your LLM applications

rags

Build ChatGPT over your data, all with natural language

MTBook

《机器翻译：基础与模型》肖桐 朱靖波 著 - Machine Translation: Foundations and Models

QAnything

Question and Answer based on Anything.

Bunny

A family of lightweight multimodal models.

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

SuperAGI

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

ChuanhuChatGPT

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

ChatDev

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

dify

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.

ChatRTX

A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM

azure-search-openai-demo

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

Verba

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

LangChain-SearXNG

AI Q&A Search Engine ➡️ 基于LangChain和SearXNG打造的开源AI搜索引擎

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

so-large-lm

大模型基础: 一文了解大模型基础知识

PyPDFForm

:fire: The Python library for PDF forms.

fast_align

Simple, fast unsupervised word aligner

mosesdecoder

Moses, the machine translation system

megablocks

Awesome-LLMs-meet-Multimodal-Generation

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models