The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

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

💬 基于 LLM 大语言模型的知识库问答系统。开箱即用，支持快速嵌入到第三方业务系统，1Panel 官方出品。

🐚 OpenDevin: Code Less, Make More

Perform data science on data that remains in someone else's server

NeMo Megatron launcher and tools

NeMo: a toolkit for conversational AI

Chat language model that can interpret and execute functions/plugins

Create a chatbot in Microsoft Word powered by ChatGPT

Data-Centric FinGPT. Open-source for open finance! Revolutionize 🔥 We release the trained model on HuggingFace.

Code for "NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video", CVPR 2021 oral

Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain ｜ 基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答

Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-…

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN,…

Chinese version of GPT2 training code, using BERT tokenizer.

Free and open fair-code licensed node based Workflow Automation Tool. Easily automate tasks across different services.

The unified platform for data-related resources.

Predictive AI layer for existing databases.

A library OS for Linux multi-process applications, with Intel SGX support

OS-agnostic, system-level binary package manager and ecosystem

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

ClearML - Model-Serving Orchestration and Repository Solution