Instructions to use wesjos/DecisionFairy-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wesjos/DecisionFairy-4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="wesjos/DecisionFairy-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("wesjos/DecisionFairy-4B")
model = AutoModelForMultimodalLM.from_pretrained("wesjos/DecisionFairy-4B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wesjos/DecisionFairy-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wesjos/DecisionFairy-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/DecisionFairy-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/wesjos/DecisionFairy-4B

SGLang

How to use wesjos/DecisionFairy-4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "wesjos/DecisionFairy-4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/DecisionFairy-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "wesjos/DecisionFairy-4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wesjos/DecisionFairy-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use wesjos/DecisionFairy-4B with Docker Model Runner:
```
docker model run hf.co/wesjos/DecisionFairy-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DecisionFairy-4B

A 4B non-autoregressive decision model: a Qwen3.5-4B backbone plus a joint schema head. One forward pass scores every option of every requested field at once — it never generates text.

Auto-generated snippets from this card only load the backbone. Typed decisions need the bundled joint_schema_model.py (or Unsloth's FastDecisionModel), as shown below.

What it does

Input is a state (a string or any JSON) plus one or more questions. Each question has a type:

`type`	meaning	answer
`noul`	yes / no	probability that it is true, `0…1`
`choice`	pick one option	best option, plus a probability per option
`score`	rate on 2–10 levels	expected level (may be fractional), plus a probability per level

All fields are decided jointly in a single pass; there is no token-by-token output. The head uses the same design as Cloudflare's Clef (projection + routing over each question and option span), and is trained with Unsloth's FastDecisionModel / DecisionTrainer.

Files

file	contents
`model.safetensors-0000{1,2}-of-00002`	Qwen3.5-4B backbone, bf16, ~4.66B params, 9.3 GB
`joint_head.safetensors`, `joint_head_config.json`	decision head: 32.05M params, 122 tensors, 64 MB (width 512, 4 blocks, 8 heads, 2 routing layers)
`joint_schema_model.py`	standalone loader + `systemone()` (torch + transformers only)
`infer.py`, `serve_systemone.py`	Unsloth-based CLI and FastAPI server
`config.json`, `tokenizer*`, `processor_config.json`, `chat_template.jinja`	base model files
`LICENSE`	Apache-2.0

Inference

Option A — standalone (`joint_schema_model.py`, no Unsloth)

from joint_schema_model import load_release_model, systemone

model, processor = load_release_model("wesjos/DecisionFairy-4B", device="cuda")  # or "cpu"

request = {
    "model": "decisionfairy",              # required by systemone()
    "state": "The production API returns 502 and p99 latency is 15s.",
    "questions": {
        "severity": {
            "type": "choice",
            "instructions": "Assign the incident tier",
            "criteria": {"P0": "total outage", "P1": "partial degradation", "P2": "minor"},
        },
        "page_oncall": {"type": "noul", "instructions": "Page the on-call engineer now?"},
        "urgency": {"type": "score", "instructions": "How urgent is it?",
                    "criteria": ["can wait", "today", "right now"]},
    },
}
print(systemone(model, processor, request, max_length=1024))

Requires a transformers build that ships Qwen3_5ForConditionalGeneration (the checkpoint was saved with transformers 5.10.4). systemone() also accepts images / videos keys on the record.

Response (same shape as the /v1/systemone API; values illustrative):

{
  "model": "decisionfairy",
  "answers": {
    "severity":    {"type": "choice", "choice": "P0", "confidence": 0.98,
                    "probabilities": {"P0": 0.98, "P1": 0.015, "P2": 0.005}},
    "page_oncall": {"type": "noul", "noul": 0.99},
    "urgency":     {"type": "score", "score": 2.1, "confidence": 0.91,
                    "legend": {"0": "can wait", "1": "today", "2": "right now"},
                    "probabilities": {"0": 0.01, "1": 0.08, "2": 0.91}}
  },
  "usage": {"input_tokens": 210, "output_tokens": 0}
}

Option B — Unsloth

from unsloth import FastDecisionModel

model, tokenizer = FastDecisionModel.from_pretrained(
    model_name="wesjos/DecisionFairy-4B",
    load_in_4bit=True,          # False for full bfloat16
    max_seq_length=1024,
)
FastDecisionModel.for_inference(model)

answers = FastDecisionModel.predict(model, tokenizer, state, questions)
for name, result in answers.items():
    print(name, result["answer"], {k: round(v, 3) for k, v in result["probabilities"].items()})

predict takes the same question format as systemone(); each answer carries answer plus the Decision API fields.

System One server

python3 serve_systemone.py --model . --port 18095        # add --load-in-4bit to halve VRAM

curl -s http://127.0.0.1:18095/v1/systemone \
  -H "Content-Type: application/json" \
  -d '{"state": "Customer says the invoice was charged twice.",
       "questions": {"refund": {"type": "noul", "instructions": "Is a refund requested?"}}}'

The wrapper accepts {state, questions} and returns {model, answers, timings}.

Notes and limits

Context: trained with max_seq_length = 1024 (unsloth_decision_config.json). Keep state + questions under ~1024 tokens, and pass max_length=1024 to systemone() (its default is 16384, which the model was never trained on).
Text decisions: the backbone architecture is multimodal and the loader accepts images / videos, but this release contains no image or video evaluation — treat it as a text model.
Probabilities are per-field softmax outputs, not calibrated on your data. Threshold on a single option's probability; confidence is not comparable across models.
No text generation: there is no LM output to read.