microsoft / DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
☆34,719Updated this week
Related projects: ⓘ
- Making large AI models cheaper, faster and more accessible☆38,614Updated this week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.☆36,446Updated this week
- Code and documentation to train Stanford's Alpaca models, and generate the data.☆29,346Updated 2 months ago
- Inference code for Llama models☆55,482Updated last month
- Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)☆25,294Updated 2 weeks ago
- Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!☆32,206Updated this week
- JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf☆23,547Updated 4 months ago
- 🦜🔗 Build context-aware reasoning applications☆92,335Updated this week
- ☆34,515Updated 8 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆36,216Updated last month
- LLM inference in C/C++☆64,973Updated this week
- Universal LLM Deployment Engine with ML Compilation☆18,642Updated this week
- OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamical…☆36,945Updated last month
- LlamaIndex is a data framework for your LLM applications☆35,450Updated this week
- The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoi…☆46,708Updated this week
- Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities☆19,545Updated 3 weeks ago
- 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.☆132,113Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆26,822Updated this week
- RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best…☆12,397Updated 2 weeks ago
- The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.☆21,016Updated 2 months ago
- 🐙 Guides, papers, lecture, notebooks and resources for prompt engineering☆47,705Updated last week
- 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.☆31,358Updated this week
- 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.☆15,839Updated this week
- Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)☆30,812Updated this week
- 🔊 Text-Prompted Generative Audio Model☆35,297Updated last month
- Instruct-tune LLaMA on consumer hardware☆18,537Updated last month
- 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.☆25,168Updated this week
- Let us control diffusion models!