Spaces:
Running
Running
|
Download README.md from Valen-Team/README: direct link, hf CLI and curl.
- Browser
- Download file 1.83 kB
-
https://huggingface.co/spaces/Valen-Team/README/resolve/main/README.md
- Command line
-
hf download hf://spaces/Valen-Team/README/README.md
-
curl -L -o README.md https://huggingface.co/spaces/Valen-Team/README/resolve/main/README.md
1.83 kB
| title: README | |
| emoji: 📉 | |
| colorFrom: yellow | |
| colorTo: blue | |
| sdk: static | |
| pinned: false | |
| # Valen | |
| **Open multimodal decision models for text, images, and video.** | |
| Valen-Decision turns inputs and questions into structured decision probabilities. Use it to classify, score, choose from a set of options, or locate with bounding boxes. | |
| <img src="https://raw.githubusercontent.com/Valen-Team/.github/main/profile/assets/valen-ecosystem.svg" alt="The Valen ecosystem: Valen-Decision-1.5 takes text, images and video with questions and returns typed answers (predicate, choice, score, bbox). Around it are the SDKs, agent skill and workflow integrations, the runtimes, evaluation with JevalKit, and Roller and Awesome-RSI for agents and recursive self-improvement." width="100%"> | |
| ## Explore | |
| 🤗 **Models:** Valen-Decision-1.5 [27B](https://huggingface.co/Valen-Team/Valen-Decision-1.5-27B) · [9B](https://huggingface.co/Valen-Team/Valen-Decision-1.5-9B) · [4B](https://huggingface.co/Valen-Team/Valen-Decision-1.5-4B) · [2B](https://huggingface.co/Valen-Team/Valen-Decision-1.5-2B) · [0.8B](https://huggingface.co/Valen-Team/Valen-Decision-1.5-0.8B) | |
| 🚀 **Try it:** [Free API Playground](https://huggingface.co/spaces/Valen-Team/Valen-API) | |
| 📊 **Evaluate:** [JevalKit Leaderboard](https://huggingface.co/spaces/Valen-Team/JevalKit-Leaderboard) · [VisualDecisionBench](https://huggingface.co/datasets/Valen-Team/VisualDecisionBench) | |
| 🛠️ **Build:** [GitHub](https://github.com/Valen-Team/Valen) · [Documentation](https://valen-team.github.io/docs/) · [Website](https://valen-team.github.io/) | |
| 🤖 **More from Valen Team:** [Roller](https://github.com/Valen-Team/Roller) turns agent runs into training data · [Documentation](https://valen-team.github.io/roller/) · [PyPI](https://pypi.org/project/roller-agent/) | |