Hugging Face adds a shared decision-model interface to Transformers
Hugging Face has introduced a shared interface across Transformers, llama.cpp, and the Hub for decision models that score predefined options instead of generating text.
AT A GLANCE
Key points
- Decision models return probability distributions over predefined options.
- Transformers now supports DecisionPipeline, AutoModelForDecision, and DecisionConfig.
- The shared interface is intended for llama.cpp, the Hub, and training tools.
What is changing?
Hugging Face has introduced a new interface that brings decision models into its ecosystem. These models take a state and a set of questions, then return structured decisions and probabilities over options already understood by the application. The approach aims to score constrained, auditable choices directly instead of generating free-form text or JSON for every task.
Transformers now includes DecisionPipeline, AutoModelForDecision, and DecisionConfig. The same contract is intended for llama.cpp serving, Hub discovery, and training tools. Hugging Face says the shared interface can connect different architectures to one application layer while leaving their internal implementations unconstrained.
Explore the original sources
Source date: 10 November 2026.
Published by AI Radar: 10 Nov 2026, 20:14 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…