JevMade

Sign in
← Back to experiments

SDKs & clients

Transformers System One serving

The transformers serve command now includes a /v1/systemone endpoint to serve any autoregressive Hugging Face model as a decision model using next-token probabilities.

Source screenshot of Transformers System One serving
SOURCE SCREENSHOTFull screenshot ↗

What it does

This endpoint reads label-token scores from an existing model rather than training a new decision model. It merged into Transformers main on 12 October, so a source install may be needed. Configuration controls the labels and prompting. Reported template-related errors and test follow-ups remain limitations.

How you can use it

Configure how the server represents the labels, then send a situation and questions with fixed answers. The server reads the chosen model’s scores for those answers without generating a reply. You are adding a decision interface to an existing model, not training another one.

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.