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
{
"name": "batch_single_question",
"states": [
"Subject: Double charged on invoice 88213\n\nHi, I was billed twice this month for the Pro plan and the second charge has not been refunded. This is the third time I have written in. If it is not fixed today I am cancelling the account.",
"Thanks, the refund arrived and everything works now.",
{
"ticket": 4821,
"message": "Subject: Double charged on invoice 88213\n\nHi, I was billed twice this month for the Pro plan and the second charge has not been refunded. This is the third time I have written in. If it is not fixed today I am cancelling the account.",
"notes": "Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. Routine checks. "
},
[
{
"role": "assistant",
"content": "How can I help?"
},
{
"role": "user",
"content": "I was billed twice this month and nobody has answered."
}
]
],
"questions": {
"cancel": {
"type": "noul",
"instructions": "The customer threatens to cancel the account."
}
},
"options": {
"batch_size": 2
},
"state_widths": [
90,
44,
147,
73
],
"results": [
{
"model": "laya-rl-agent-onnx",
"answers": {
"cancel": {
"type": "noul",
"noul": 0.0414,
"confidence": 0.9586,
"answer_confidence": 0.9586,
"action": {
"act_probability": 1.0
}
}
},
"usage": {
"input_tokens": 90,
"output_tokens": 0,
"state_tokens": 56,
"state_tokens_dropped": 0,
"truncated": false,
"truncated_questions": []
}
},
{
"model": "laya-rl-agent-onnx",
"answers": {
"cancel": {
"type": "noul",
"noul": 0.0067,
"confidence": 0.9933,
"answer_confidence": 0.9933,
"action": {
"act_probability": 1.0
}
}
},
"usage": {
"input_tokens": 44,
"output_tokens": 0,
"state_tokens": 10,
"state_tokens_dropped": 0,
"truncated": false,
"truncated_questions": []
}
},
{
"model": "laya-rl-agent-onnx",
"answers": {
"cancel": {
"type": "noul",
"noul": 0.1873,
"confidence": 0.8127,
"answer_confidence": 0.8127,
"action": {
"act_probability": 1.0
}
}
},
"usage": {
"input_tokens": 147,
"output_tokens": 0,
"state_tokens": 113,
"state_tokens_dropped": 0,
"truncated": false,
"truncated_questions": []
}
},
{
"model": "laya-rl-agent-onnx",
"answers": {
"cancel": {
"type": "noul",
"noul": 0.0166,
"confidence": 0.9834,
"answer_confidence": 0.9834,
"action": {
"act_probability": 1.0
}
}
},
"usage": {
"input_tokens": 73,
"output_tokens": 0,
"state_tokens": 39,
"state_tokens_dropped": 0,
"truncated": false,
"truncated_questions": []
}
}
],
"runs": [
[
2,
90
],
[
2,
147
]
]
}