Draft preview. Not yet published. Items marked TODO are unconfirmed.

Overview

SauerkrautLM-decision takes an input (the state) and one or more typed questions, and returns one structured answer per question. Instead of free text, it returns probabilities your code can threshold, route on or rank by. TODO: one or two sentences on what the model is built for and what it was trained on.

  • Yes/No answers

    A single probability that the answer is "yes", ready to threshold.

  • Choice and Score

    Pick one option from a set, or place the input on an ordered scale, each with a full probability distribution.

  • Several questions per call

    All questions are evaluated against the same input in one call.

Specifications

PropertyValue
ParametersTODO
Context lengthTODO
ArchitectureTODO
InputsTODO (text only, or text and images?)
OutputsProbabilities per question (Yes/No, Choice, Score). TODO confirm
Precisionbf16
Checkpoint size (bf16)TODO
Minimum GPU memoryTODO
Hugging FaceVAGOsolutions/SauerkrautLM-decision (TODO confirm repo name)
LicenseTODO

Quick Start

Install:

bash
pip install -U transformers torch accelerate

TODO: confirm the minimum transformers version.

Load the model and ask three questions about one input:

python
from transformers import AutoModel

model_id = "VAGOsolutions/SauerkrautLM-decision"  # TODO confirm repo name
model = AutoModel.from_pretrained(
    model_id,
    trust_remote_code=True,
    dtype="bfloat16",
    device_map="auto",
)

state = "Ich wurde diesen Monat doppelt belastet, bitte erstatten Sie eine Zahlung."
questions = {
    "refund": {
        "type": "noul",
        "instructions": "Is the customer asking for a refund?",
    },
    "team": {
        "type": "choice",
        "instructions": "Which team should handle this?",
        "criteria": {
            "billing": "Charges, refunds, invoices",
            "technical": "App or website faults",
            "account": "Login, profile or subscription changes",
        },
    },
    "urgency": {
        "type": "score",
        "instructions": "How urgent is this?",
        "criteria": ["Can wait", "Handle today", "Blocking the customer now"],
    },
}

output = model.system_one(state, questions)
print(output)

TODO: confirm that the remote code exposes system_one and these question type names.

Request format

FieldDescription
stateThe input to evaluate: plain text or a JSON-serialisable object.
questionsNamed questions. Each has a type (noul, choice or score), instructions, and for Choice and Score, criteria.
imagesTODO: only if image input is supported.

Question types

Type noul. Returns one probability between 0 and 1 that the answer is "yes". Values near 0 or 1 are clear answers; values near 0.5 mean the model is unsure.

python
questions = {
    "is_complaint": {
        "type": "noul",
        "instructions": "Is this message a complaint?",
    }
}

Answer shape (TODO confirm):

json
{ "is_complaint": { "type": "noul", "noul": "TODO" } }

Using the answer

Because answers are numbers, the decision logic stays in your code:

python
p = output["refund"]["noul"]  # TODO confirm output structure

if p > 0.8:
    action = "auto_refund"
elif p < 0.2:
    action = "no_refund"
else:
    action = "human_review"

The 0.8 / 0.2 thresholds are an example. Tune them on your own data.

Deployment

SauerkrautLM-decision is published as a single bf16 checkpoint. No GGUF, MLX, W8A8 or other quantized variants are provided. Plan for at least TODO GB of GPU memory. For hosted access without your own GPU, see the SauerkrautLM-decision API.