Aria

About

What Aria is

Aria Model Card [Dec 1, 2024] We have released the base models (with native multimodal pre-training) for Aria (Aria-Base-8K and Aria-Base-64K) for research purposes and continue training. - Aria is the first open multimodal native MoE model, capable of seamlessly handling various input modalities within a MoE architecture. - Aria performs on par with GPT-4o mini and Gemini 1.5 Flash across a range of multimodal tasks while maintaining strong performance on text-only tasks. - Compared to similar or even larger models, Aria boasts faster speeds and lower costs. This high efficiency stems from its ability to activate only 3.9B parameters during inference – the fewest among models with comparable performance. -- Key features - SoTA Multimodal Native Performance: Aria achieves strong performance on a wide range of multimodal, language, and coding tasks. It is superior in video and document understanding. - Lightweight and Fast: Aria is a mixture-of-expert model with 3.9B activated parameters per token. It efficently encodes visual input of variable sizes and aspect ratios. - Long Multimodal Context Window: Aria supports multimodal input of up to 64K tokens. It can caption a 256-frame video in 10 seconds. 🔗 <a href="https://rhymes.ai/" target="blank" Try Aria!</a · 📖 <a href="https://www.rhymes.ai/blog-details/aria-first-open-multimodal-native-moe-model" target="blank"Blog</a · 📌 <a href="https://arxiv.org/pdf/2410.05993" target="blank"Paper</a · ⭐ <a href="https://github.com/rhymes-ai/Aria" target="blank"GitHub</a · 🟣 <a href="https://discord.com/invite/u8HxU23myj" target="blank" Discord </a Benchmark Quick Start Installation Inference Aria has 25.3B total parameters, it can be loaded in one A100 (80GB) GPU with bfloat16 precision. Here is a code snippet to show you how to use Aria. From transformers=v4.48, you can also pass image url or local path to the conversation history, and let the chat template handle the rest. Chat template will load the image for you and return inputs in torch.Tensor which you can pass directly to model.generate(). Here is how to rewrite the above example Advanced Inference and Fine-tuning We provide a codebase for more advanced usage of Ar

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys aria for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (aria below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"aria","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More language models