serving/README.md

Pivot serving interfaces

The model exposes three synchronous methods after loading AutoModel and AutoTokenizer with trust_remote_code=True:

1. choose(tokenizer, context, options) returns a simple choice, index and probability vector.
2. decide_native(tokenizer, context, candidates) accepts stable machine IDs, semantic candidate text and at most one explicit abstain candidate.
3. decide(tokenizer, state, questions) returns a typed collection of choice, yes/no and score decisions.

The model operates on supplied options; it does not create new options or generate explanatory text. The default serving limits in this update are 512 context tokens and 128 tokens per option. Keep a stable option set if comparing scores between requests.

The pre-existing typed request and response and native request and response illustrate the wire shapes. Run a typed Python example or read the full inference guide.