jul-decision-e5-small

multilingual-e5-small trained to answer jul decisions: Choice, yes/no (Noul) and Score. Small enough to run inside an AWS Lambda function. ONNX 8-bit build: usejul/jul-decision-e5-small-onnx.

jul models add jul-decision-e5-small --repo usejul/jul-decision-e5-small-onnx --backend onnx

Two sets of weights, same size (e5-small):

• the root: vectors. Text and options are encoded apart and compared; reads Choice, and every question tuned with autotune. Inputs are prefixed with query: .
• cross/: a cross model. The question and the text are read together; reads Noul and Score with no labeled examples. jul models add attaches it by itself; jul pack ships only the part a deployment needs.

Results

Jev bench (AG News, Banking77, Emotion; Choice only, so the vectors), ONNX 8-bit, 4 ms per text:

	e5-small	jul-decision-e5-small
zero-shot	0.543	0.557
autotune, hybrid head (1,000 labels)	0.790	0.780

Kev's typed decisions (transfer-v9 development split, clean questions, never trained on), through jul:

	yes/no	Choice	Score	all
vectors only	0.579	0.401	0.275	0.460
with the cross model	0.726	0.401	0.500	0.524

The cross model: paraphrase 0.50 → 0.79, inference (QNLI) 0.55 → 0.70, offensive posts 0.725 → 0.80; "is the customer angry?" 0.84–0.99 on angry support messages, 0.00–0.02 on calm ones.

Not good at: urgency, hard but polite complaints (read as offensive), sentences with the same words in another order, knowledge questions. With few labels per task, tune: zero-shot is a starting point.

Training

jul's own score as the loss (vectors), and a cross-entropy over pairs with one head per question type (cross model), on public English and French datasets under commercial-use licenses: classification, tool routing, moderation, paraphrase, inference, compositions, dates and tone. Embeddings frozen for the vectors. One GPU.

Versions

v2.0 (this one): stage-2 vectors and the cross model. v1.0: the first vectors, without cross/ (revision="v1.0").

License

Apache-2.0. Based on multilingual-e5-small (MIT).