Unify Efficient Fine-Tuning of 100+ LLMs

AI-powered multi-agent builder

KubeIaaS is a feature-rich and user-friendly private IaaS cloud solution based on Kubernetes. (基于 Kubernetes 的易于部署和运维、功能完备且易用的私有 IaaS 云解决方案)

微信机器人底层框架，可接入Gemini、ChatGPT、ChatGLM、讯飞星火、Tigerbot等大模型。WeChat Robot Hook.

🚀LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training

Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A powerful little TUI framework 🏗

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

🔥 🔥 🔥 现代化、开源的 Linux 服务器运维管理面板。

Feishu(飞书)/Lark Open API Go SDK, Support ALL Open API and Event Callback.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

将llama3的MLP复制8份构建基于llama3的8×8b MoE模型

LLM API Server , OpenAI 同时支持 ChatGLM3 ，Llama, Llama-3, Firefunction, Openfunctions ，BAAI/bge-m3 ,bge-large-zh-v1.5

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

"Video-ChatGPT" is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotem…

The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Inference code for CodeLlama models

OpenAIOS vGPU device plugin for Kubernetes is originated from the OpenAIOS project to virtualize GPU device memory, in order to allow applications to access larger memory space than its physical ca…

Grok open release

Open-Sora: Democratizing Efficient Video Production for All

中文Mixtral混合专家大模型（Chinese Mixtral MoE LLMs）

Ongoing research training transformer models at scale

This is the codebase for pre-training, compressing, extending, and distilling LLMs with Megatron-LM.

The framework to prune LLMs to any size and any config.

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training