|
Download README.md from helmo/decida: direct link, hf CLI and curl.
- Browser
- Download file 1.05 kB
-
https://huggingface.co/spaces/helmo/decida/resolve/main/README.md
- Command line
-
hf download hf://spaces/helmo/decida/README.md
-
curl -L -o README.md https://huggingface.co/spaces/helmo/decida/resolve/main/README.md
1.05 kB
| title: Decida | |
| emoji: π | |
| colorFrom: indigo | |
| colorTo: gray | |
| sdk: gradio | |
| sdk_version: 5.9.1 | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| short_description: Typed decisions in one forward pass, free on ZeroGPU. | |
| # Decida | |
| A free ZeroGPU demo of [DecidaBERT-large](https://huggingface.co/helmo/DecidaBERT-large): send a **state** and | |
| typed **questions** (`choice`, `score`, `noul`), get a probability distribution per question back from a single | |
| forward pass, no generated text. | |
| This Space's code (`app.py`, `model.py`) is independent of the main project β it re-implements the model's decision | |
| heads and prompt layout directly against the public checkpoint, since ZeroGPU only supports the Gradio SDK, not a | |
| plain REST server. The real thing β a local runtime with a REST API, MCP tools and a full testbench of games β | |
| is at **https://github.com/heldernoid/decida**, and runs the same model (plus Qwen3-0.6B and the Laya family) | |
| locally, on your own hardware. | |
| Not affiliated with TypeSafe, Convai Innovations or any other model author. | |