基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT3.5/GPT-4o/GPT-o1/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.

DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including x86 and ARMv9.

Alpaca Chinese Dataset -- 中文指令微调数据集【持续更新】

Inference and training library for high-quality TTS models.

Deep Learning System core principles introduction.

《Hello 算法》：动画图解、一键运行的数据结构与算法教程，支持 Python, C++, Java, C#, Go, Swift, JS, TS, Dart, Rust, C, Zig 等语言。English edition ongoing

A Ray-based High-performance RLHF framework (Support 70B+ full tuning & LoRA & Mixtral)

Accurate line-level text detection and recognition (OCR) in any language

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Simple samples for TensorRT programming

🤖 Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your p…

LLM Inference benchmark

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

EMNLP 2023: Instructive Dialogue Summarization with Query Aggregations

一键自动化 下载、安装、激活 Office 的利器。

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

The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.

实现一种单/多Lora-Fusion权值交叉融合+Zero-Finetune零微调增强的跨模型技术方案，LLM-Base+LLM-X+Alpaca，初期，LLM-Base为Chatglm6B底座模型，LLM-X是LLAMA增强模型。该方案简易高效，目标是使此类语言模型能够低能耗广泛部署，并最终在小模型的基座上发生“智能涌现”，力图最小计算代价达成ChatGPT、GPT4、ChatRWKV等人…

Summarize all low-cost replication methods for Chatgpt. It is believed that with the improvement of data and model fine-tuning techniques, small models suitable for various segmented fields will co…

Making large AI models cheaper, faster and more accessible

中文LLaMA&Alpaca大语言模型+本地部署 (Chinese LLaMA & Alpaca LLMs)

Automatically split your PyTorch models on multiple GPUs for training & inference

Jupyter notebooks for the Natural Language Processing with Transformers book

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

The definitive guide to using Vector Search to solve your semantic search production workload needs.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.