|
|
--- |
|
|
title: README |
|
|
emoji: 🏃 |
|
|
colorFrom: indigo |
|
|
colorTo: red |
|
|
sdk: streamlit |
|
|
pinned: false |
|
|
--- |
|
|
|
|
|
<h1 style="display: flex; align-items: center; margin-bottom: -2em;" > |
|
|
<span>Red Hat AI </span> |
|
|
<img width="40" height="40" alt="tool icon" src="https://upload.wikimedia.org/wikipedia/commons/thumb/d/d8/Red_Hat_logo.svg/2560px-Red_Hat_logo.svg.png" /> |
|
|
<span> Build AI for your world</span> |
|
|
</h1> |
|
|
|
|
|
Red Hat AI is powered by open-source with partnerships with IBM Research and Red Hat AI Business Units. |
|
|
|
|
|
We strongly believe the future of AI is open and community-driven research will propel AI forward. |
|
|
As such, we are hosting our latest optimized models on Hugging Face, fully open for the world to use. |
|
|
We hope that the AI community will find our efforts useful and that our models help fuel their research. |
|
|
|
|
|
With Red Hat AI you can, |
|
|
- Access and leverage quantized variants of the leading open source models cush as Llama 4, Mistral Small 3.1, Phi 4, Granite and more. |
|
|
- Tune smaller, purpose-built models with your own data. |
|
|
- Quantize your models with [LLM Compressor](https://github.com/vllm-project/llm-compressor) or use our pre-optimized models on HuggingFace. |
|
|
- Optimize inference with [vLLM](https://github.com/vllm-project/vllm). |
|
|
|
|
|
We provide accurate model checkpoints compressed with SOTA methods ready to run in vLLM such as W4A16, W8A16, W8A8 (int8 and fp8), and many more! |
|
|
If you would like help quantizing a model or have a request for us to add a checkpoint, please open an issue in https://github.com/vllm-project/llm-compressor. |
|
|
|
|
|
Learn more at https://www.redhat.com/en/products/ai |
|
|
|
|
|
|
