Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Python calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorchroutingtyped-decisionszero-shot
ci: run the Spanish phone-turn benchmark audit and tests
Freddy Chinchilla050059cf5442
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.ymlindex 39843b20..c4ba71df 100644--- a/.github/workflows/ci.yml+++ b/.github/workflows/ci.yml@@ -60,6 +60,9 @@ jobs:# This job installs nothing, so running the audit here is what proves it needs# nothing but the standard library. Its test suite imports numpy and runs in `test`.- run: python research/benchmarks/zh_short_commands/audit.py+ # Standard library only, audit and tests alike, so both run here.+ - run: python research/benchmarks/es_phone_turns/audit.py+ - run: python -m unittest discover -s research/benchmarks/es_phone_turns/tests -vtest:name: tests (py${{ matrix.python }})