---
title: "Decision Models in Hugging Face"
description: "Decision models evaluate a state against typed questions—choice, score, or noul—and return a probability distribution over predefined answers without generating text. Unlike traditional classifiers, they accept runtime-defined labels, and unlike zero-shot classifiers, they handle multiple typed questions per request. The interface is State + Questions + Allowed Answers → Decisions + Probabilities, with models like JEV-9B available on the Hugging Face Hub under a dedicated tag, and the ecosystem includes encoder-based and generative backbone models. Hugging Face’s transformers library supports inference via a pipeline and fine-tuning via the Trainer API, with a toy example fine-tuning JEV-9B to route support requests to billing, shipping, or technical categories using cross-entropy loss. Decision models make decisions and probabilities first-class outputs, optimized for reliable, calibrated decisions in software, and are designed to be more efficient than prompting LLMs for structured tasks."
---

# Decision Models in Hugging Face

[Hugging Face](https://yomu.fyi/company/hugging-face) · Aritra Roy Gosthipaty, Lysandre, Pedro Cuenca, Tom Aarsen · Nov 10, 2026

**Type:** Explainer

## Summary

Decision models evaluate a state against typed questions—choice, score, or noul—and return a probability distribution over predefined answers without generating text. Unlike traditional classifiers, they accept runtime-defined labels, and unlike zero-shot classifiers, they handle multiple typed questions per request. The interface is State + Questions + Allowed Answers → Decisions + Probabilities, with models like JEV-9B available on the Hugging Face Hub under a dedicated tag, and the ecosystem includes encoder-based and generative backbone models. Hugging Face’s transformers library supports inference via a pipeline and fine-tuning via the Trainer API, with a toy example fine-tuning JEV-9B to route support requests to billing, shipping, or technical categories using cross-entropy loss. Decision models make decisions and probabilities first-class outputs, optimized for reliable, calibrated decisions in software, and are designed to be more efficient than prompting LLMs for structured tasks.

## Context

Hugging Face blog post introducing decision models, their interface, and how to use them with the transformers library.

## Approach / What changed

Decision models are implemented in Hugging Face’s transformers library with a dedicated pipeline and AutoModelForDecision class, supporting inference and fine-tuning via the Trainer API.

## Takeaways

- Decision models return a probability distribution over predefined answers without generating text, using typed questions (choice, score, noul) evaluated against a state.
- Unlike traditional classifiers, decision models accept runtime-defined labels, and unlike zero-shot classifiers, they support multiple typed questions in a single request.
- Hugging Face provides a decision model tag on the Hub, a pipeline for inference, and a Trainer API for fine-tuning, with TRL support forthcoming.

## FAQ

### What are decision models?

Decision models take a state and typed questions (choice, score, noul) and return a probability distribution over predefined answers without generating text. They are designed for structured decision-making tasks like routing and classification.

### How do decision models differ from zero-shot classification?

Decision models extend zero-shot classification by supporting multiple typed questions per request, including choice, score, and noul primitives, and are optimized for reliable, calibrated decisions with a consistent interface.

### How can I fine-tune a decision model in Hugging Face?

You can fine-tune decision models using the Trainer API with a custom compute\_loss function that applies cross-entropy loss on the logits for choice questions. The model.decision\_config.prepare\_inputs method converts state and questions into model inputs.

**Tags:** [Classification](https://yomu.fyi/topic/classification), [Decision Models](https://yomu.fyi/topic/decision-models), [Hugging Face](https://yomu.fyi/topic/hugging-face), [Transformers](https://yomu.fyi/topic/transformers)

- Source: [Hugging Face](https://huggingface.co/blog/decision)
- Source URL: https://huggingface.co/blog/decision
- Ingested by Yomu: 2026-11-10T18:01:09.117Z

[Read original post](https://huggingface.co/blog/decision)
