AI on demand: Mapika/decider-31b - Revision history

Sst-djo: /* Overview */

2026-10-19T08:35:02Z

Overview

← Older revision		Revision as of 10:35, 19 October 2026
Line 14:		Line 14:
	These models suit classification, routing, and decision support. They do not generate conversational answers or explanations, and their predictions can be wrong. Reported probabilities require evaluation on representative data before using them for consequential automation.		These models suit classification, routing, and decision support. They do not generate conversational answers or explanations, and their predictions can be wrong. Reported probabilities require evaluation on representative data before using them for consequential automation.

	Our [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] implementation has a multilingual checkpoint with a fixed ~~65'536~~-token input limit.		Our [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] implementation has a multilingual checkpoint with a fixed 40960-token input limit.

	= Usage =		= Usage =

Sst-mei: /* Usage - Score */

2026-10-18T09:18:32Z

Usage - Score

← Older revision		Revision as of 11:18, 18 October 2026
Line 191:		Line 191:
	</syntaxhighlight>		</syntaxhighlight>

	[[Category:AI on ~~demand~~]]		[[Category:AI on Demand]]
			[[Category: System One decision models]]

Sst-mei: /* Usage - Score */

2026-10-18T08:57:38Z

Usage - Score

← Older revision		Revision as of 10:57, 18 October 2026
Line 162:		Line 162:
	"urgency": {		"urgency": {
	"type": "score",		"type": "score",
	"score": 3.~~9722~~,		"score": 3.9,
			"confidence": 0.915,
			"x_p_max": 0.9466,
			"certainty": 0.8337,
	"legend": {		"legend": {
	"0": "Not urgent: informational request with no operational impact",		"0": "Not urgent: informational request with no operational impact",
Line 171:		Line 174:
	},		},
	"probabilities": {		"probabilities": {
	"0": 0.~~0001~~,		"0": 0.0076,
	"1": 0.~~0001~~,		"1": 0.011,
	"2": 0.~~0003~~,		"2": 0.0039,
	"3": 0.~~0264~~,		"3": 0.031,
	"4": 0.~~9731~~		"4": 0.9466
	},		}
	~~"confidence": 0.9769~~
	}		}
	},		},
	"usage": {		"usage": {
	"input_tokens": 91,		"input_tokens": 140,
	"output_tokens": ~~162~~,		"output_tokens": 0,
	"prompt_tokens": 91,		"prompt_tokens": 140,
	"completion_tokens": ~~162~~		"completion_tokens": 0
	},		}
	~~"latency_ms": 99.0~~
	}		}
	</syntaxhighlight>		</syntaxhighlight>

	[[Category:AI on demand]]		[[Category:AI on demand]]

Sst-mei: /* Usage - Noul */

2026-10-18T08:57:06Z

Usage - Noul

← Older revision		Revision as of 10:57, 18 October 2026
Line 85:		Line 85:

	# Execute the actual call:		# Execute the actual call:
	~~curl --fail-with-body -sS \~~		{
	~~https://llm.stoney-cloud.com/v1/systemone \~~		"model": "Mapika/decider-31b",
	~~-H "apikey: $STONEY_KEY" \~~		"answers": {
	~~-H 'Content-Type: application/json' \~~		"refund_requested": {
	~~--data-binary '{~~		"type": "noul",
	"model": "Mapika/decider-31b",		"noul": 0.9327
	"~~state~~": {
	~~"document": "Meine Rechnung wurde zweimal belastet. Bitte erstatten Sie mir die zweite Zahlung zurück."~~
	},
	"~~questions~~": {
	~~"refund_requested": {~~
	"type": "noul",
	"~~instructions~~": ~~"Does the customer explicitly request a refund?",~~
	~~"criteria": {~~
	~~"true": "The customer explicitly asks for money to be returned.",~~
	~~"false": "The customer does not ask for money to be returned~~."
	}
	}
	}		}
	}~~' \| jq .~~		},
			"usage": {
			"input_tokens": 89,
			"output_tokens": 0,
			"prompt_tokens": 89,
			"completion_tokens": 0
			}
			}
	</syntaxhighlight>		</syntaxhighlight>

Sst-mei: /* Usage - Choice */

2026-10-18T08:56:32Z

Usage - Choice

← Older revision		Revision as of 10:56, 18 October 2026
Line 57:		Line 57:
	"type": "choice",		"type": "choice",
	"choice": "billing",		"choice": "billing",
	"confidence": 0.~~9985~~,		"confidence": 0.9264,
			"x_p_max": 0.9509,
			"certainty": 0.795,
	"probabilities": {		"probabilities": {
	"technical": 0.~~0003~~,		"technical": 0.0351,
	"billing": 0.~~999~~,		"billing": 0.9509,
	"support": 0.~~0007~~		"support": 0.014
	}		}
	}		}
	},		},
	"usage": {		"usage": {
	"input_tokens": 59,		"input_tokens": 88,
	"output_tokens": 62,		"output_tokens": 0,
	"prompt_tokens": 59,		"prompt_tokens": 88,
	"completion_tokens": 62		"completion_tokens": 0
	},		}
	~~"latency_ms": 45.9~~
	}		}
	</syntaxhighlight>		</syntaxhighlight>

Sst-mei: Created page with "= Overview = System One decision models such as [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] assess text and return structured answers and probabilities in a single forward pass. They support three question types: * '''Choice''' ** Selects the single best option (or returns a probability distribution) from a fixed set of 2 to 255 declared options. * '''Noul (Yes/No)''' ** Returns a boolean probability distribution for a binary question. * '''Score..."

2026-10-18T08:55:53Z

Created page with "= Overview = System One decision models such as [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] assess text and return structured answers and probabilities in a single forward pass. They support three question types: * '''Choice''' ** Selects the single best option (or returns a probability distribution) from a fixed set of 2 to 255 declared options. * '''Noul (Yes/No)''' ** Returns a boolean probability distribution for a binary question. * '''Score..."

New page

= Overview =
System One decision models such as [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] assess text and return structured answers and probabilities in a single forward pass.

They support three question types:
* '''Choice'''
** Selects the single best option (or returns a probability distribution) from a fixed set of 2 to 255 declared options.

* '''Noul (Yes/No)'''
** Returns a boolean probability distribution for a binary question.

* '''Score'''
** Assigns a numeric value along a defined ordered scale (typically 2 to 10 levels) to represent a grading rubric or rating.

These models suit classification, routing, and decision support. They do not generate conversational answers or explanations, and their predictions can be wrong. Reported probabilities require evaluation on representative data before using them for consequential automation.

Our [https://huggingface.co/Mapika/decider-31b Mapika/decider-31b] implementation has a multilingual checkpoint with a fixed 65'536-token input limit.

= Usage =
== Usage - Choice ==
The following '''choice''' example routes a request to a department.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "Mapika/decider-31b",
"state": {
"document": "Meine Rechnung wurde zweimal belastet. Bitte prüfen Sie die doppelte Zahlung."
},
"questions": {
"department": {
"type": "choice",
"instructions": "Which department should handle this request?",
"criteria": {
"technical": "Application errors and login problems",
"billing": "Invoices, payments and duplicate charges",
"support": "General customer support and newsletter preferences"
}
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
{
"model": "Mapika/decider-31b",
"answers": {
"department": {
"type": "choice",
"choice": "billing",
"confidence": 0.9985,
"probabilities": {
"technical": 0.0003,
"billing": 0.999,
"support": 0.0007
}
}
},
"usage": {
"input_tokens": 59,
"output_tokens": 62,
"prompt_tokens": 59,
"completion_tokens": 62
},
"latency_ms": 45.9
}
</syntaxhighlight>

== Usage - Noul ==
The following '''noul''' example detects if customer explicitly requests a refund.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "Mapika/decider-31b",
"state": {
"document": "Meine Rechnung wurde zweimal belastet. Bitte erstatten Sie mir die zweite Zahlung zurück."
},
"questions": {
"refund_requested": {
"type": "noul",
"instructions": "Does the customer explicitly request a refund?",
"criteria": {
"true": "The customer explicitly asks for money to be returned.",
"false": "The customer does not ask for money to be returned."
}
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
"model": "Mapika/decider-31b",
"answers": {
"refund_requested": {
"type": "noul",
"noul": 0.9851
}
},
"usage": {
"input_tokens": 60,
"output_tokens": 23,
"prompt_tokens": 60,
"completion_tokens": 23
},
"latency_ms": 86.9
}
</syntaxhighlight>

== Usage - Score ==
The following '''score''' example estimates the urgency of a support request. The criteria is arranged from lowest to highest.

Example call:
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-....

# Execute the actual call:
curl --fail-with-body -sS \
https://llm.stoney-cloud.com/v1/systemone \
-H "apikey: $STONEY_KEY" \
-H 'Content-Type: application/json' \
--data-binary '{
"model": "Mapika/decider-31b",
"state": {
"document": "Unser gesamtes Produktionssystem ist ausgefallen. Alle Kunden sind betroffen und können keine Bestellungen aufgeben. Wir benötigen sofort Hilfe."
},
"questions": {
"urgency": {
"type": "score",
"instructions": "How urgent is this support request?",
"criteria": [
"Not urgent: informational request with no operational impact",
"Low urgency: minor inconvenience with a workaround",
"Moderate urgency: partial disruption affecting some users",
"High urgency: major disruption requiring prompt attention",
"Critical urgency: complete production outage affecting all customers"
]
}
}
}' | jq .
</syntaxhighlight>

Example answer:
<syntaxhighlight lang="json">
{
"model": "Mapika/decider-31b",
"answers": {
"urgency": {
"type": "score",
"score": 3.9722,
"legend": {
"0": "Not urgent: informational request with no operational impact",
"1": "Low urgency: minor inconvenience with a workaround",
"2": "Moderate urgency: partial disruption affecting some users",
"3": "High urgency: major disruption requiring prompt attention",
"4": "Critical urgency: complete production outage affecting all customers"
},
"probabilities": {
"0": 0.0001,
"1": 0.0001,
"2": 0.0003,
"3": 0.0264,
"4": 0.9731
},
"confidence": 0.9769
}
},
"usage": {
"input_tokens": 91,
"output_tokens": 162,
"prompt_tokens": 91,
"completion_tokens": 162
},
"latency_ms": 99.0
}
</syntaxhighlight>

[[Category:AI on demand]]