|
Download README.md from MachinePulseAI/karpo-decision-31B: direct link, hf CLI and curl.
- Browser
- Download file 2.42 kB
-
https://huggingface.co/spaces/MachinePulseAI/karpo-decision-31B/resolve/main/README.md
- Command line
-
hf download hf://spaces/MachinePulseAI/karpo-decision-31B/README.md
-
curl -L -o README.md https://huggingface.co/spaces/MachinePulseAI/karpo-decision-31B/resolve/main/README.md
2.42 kB
A newer version of the Gradio SDK is available: 6.32.0
metadata
title: karpo-decision-31B
emoji: ⚖️
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 6.31.0
app_file: app.py
short_description: Typed decisions from one forward pass — choice, noul, score
python_version: '3.12'
startup_duration_timeout: 1h
karpo-decision-31B — decision model playground
MachinePulseAI/karpo-decision-31B is a 31.3B decision model, ranked #1 on the Decision Index (Full score 73.9). Fine-tuned from google/gemma-4-31B-it, it replaces text generation with a linear readout: given a state — any text or JSON — and a schema of typed questions, it returns a probability for every option of every question in one forward pass.
How to use
- Describe the situation in the State box (plain text or a JSON value).
- Write questions as JSON — one object per question, keyed by question ID. Each question has a
type(choice/noul/score), optionalinstructions, andcriteria:- choice —
criteriamaps option keys to descriptions. - noul — true/false;
criteriais an optional{"false": ..., "true": ...}. - score —
criteriais a list of at least two ordered level descriptions, lowest first.
- choice —
- Press Decide. Each answer renders as a probability distribution with the chosen option (or expected level, or probability of true) and a confidence margin; the raw System One JSON response is in the accordion below.
All questions are answered in a single forward pass — the model reads the state once, and no question sees another question's options. Text only, up to 32,768 tokens per sequence (a longer request is split by questions, each part with the full state).
Notes
- Probabilities are relative to the options you supply: adding or changing an option changes the distribution.
- The model always picks one of the given options; it never generates text.
- The inference code is the authors' karpo-decision package (Apache-2.0), vendored in this Space.
Powered by karpo-decision (MachinePulse). Weights under Apache-2.0.