README.md

---
pipeline_tag: zero-shot-classification
license: apache-2.0
base_model: Qwen/Qwen3.5-2B
base_model_relation: finetune
tags:
- zero-shot-classification
- multilingual
- decision-model
- classification
- qwen3_5
- pytorch
---

![Open Decision Foundation Models — Sol-2B](assets/decision-sol-2b-header.png)


# Decision-1.0-Sol-2B

*Sol, Latin for sun.*

Give Sol a state, questions and possible answers. It returns decisions and probabilities with labels defined at runtime.


[Decision family](https://huggingface.co/collections/vllm-sr/decision-10-6ab12177bd0002394d8409f9)

| Type | Use it for | Output |
|---|---|---|
| **Choice** | Route a request or choose among 2–255 actions. | Selected ID + distribution |
| **Noul** | Check a condition against supplied evidence. | P(true) |
| **Score** | Apply 2–10 ordered rubric descriptions. | Expected index + distribution |

## Measured capability

**66.32% weighted accuracy** across 3,766 decisions and 54 tasks. Compare decision, reading and transfer capabilities in the complete results below.

| Model | Size | Decisions | Composition | Reading | Inference | Transfer | Overall |
|---|---:|---:|---:|---:|---:|---:|---:|
| Sol-2B | 2B | 73.75 | 46.08 | 76.56 | 84.17 | 57.07 | 66.32 |
| Lux-9B | 9B | **84.38** | **52.75** | 90.16 | **91.46** | 77.72 | **77.40** |
| Nox-4B | 4B | **83.00** | **51.79** | 79.06 | **86.25** | 69.60 | **73.09** |
| Kev-9B | 9B | 76.75 | 45.75 | 86.72 | 83.54 | 79.25 | 71.89 |
| Kev-4B | 4B | 71.90 | 48.54 | 81.88 | 84.58 | 76.10 | 70.09 |
| Qwen3.5-9B | 9B | 73.91 | 44.62 | 89.84 | 79.58 | 73.23 | 69.73 |
| Decider | 2B | 64.01 | 46.58 | 92.03 | 84.38 | 69.31 | 67.71 |
| Qwen3.5-4B | 4B | 69.89 | 43.33 | 87.97 | 79.79 | 68.83 | 67.29 |
| Eos-0.8B | 0.8B | 65.94 | 46.04 | 70.31 | 81.67 | 52.01 | 61.89 |
| Kev-0.8B | 0.8B | 60.14 | 42.29 | 67.81 | 68.75 | 61.19 | 58.28 |
| Qwen3.5-2B | 2B | 57.12 | 39.00 | 73.75 | 72.29 | 56.31 | 57.24 |
| Kai-0.6B | 0.6B | 57.96 | 40.83 | 54.69 | 69.79 | 48.37 | 53.52 |
| Laya · English | 0.421B | 56.54 | 35.33 | 51.41 | 63.75 | 53.06 | 51.03 |
| Laya · Multilingual | 0.322B | 47.25 | 38.92 | 50.78 | 57.29 | 47.13 | 47.19 |
| Jev | — | 79.10 | 66.38 | 94.53 | 89.79 | 87.19 | 81.05 |

Accuracy (%). Overall weights: Decisions **30%**, Composition **25%**, Reading **15%**, Inference **15%**, Transfer **15%**. These outcome-informed product-priority weights were chosen after observing results. Bold marks a Decision-family cell above every external open or untuned reference; Jev and other Decision models are excluded.

![Decision model ranking](assets/decision-ranking.png)

![Capability matrix](assets/decision-matrix.png)

[All 54 tasks](evaluation/TASKS.md) · [Probability, order and missing-evidence diagnostics](evaluation/DIAGNOSTICS.md) · [Methods and uncertainty](evaluation/EVALUATION.md)

## More questions, measured

![Question-count latency](assets/decision-question-scaling.png)

Distinct Choice questions at a fixed **499 input tokens per question**. Thirty measurements per point across six independently loaded processes on an otherwise idle AMD gfx942 GPU. Python request latency includes tokenization and inference; loading and network are excluded. [p50, p95 and memory](evaluation/QUESTION-SCALING.md).

## Download the complete model repository

```bash
hf download vllm-sr/Decision-1.0-Sol-2B --local-dir Decision-1.0-Sol-2B
```

This downloads the complete model release. The root `config.json` lists the backbone, tokenizer, decision head, and calibration files.

## Use with 🤗 Transformers

The repository includes its inference code, so stock Transformers can download and run the complete model locally with `trust_remote_code=True`. `system_one` takes and returns the same System One request and response bodies as the Decision runtime; nothing is generated.

```bash
pip install "transformers>=5.17" torch safetensors huggingface_hub
```

```python
from transformers import AutoModel

model = AutoModel.from_pretrained("vllm-sr/Decision-1.0-Sol-2B", trust_remote_code=True)
response = model.system_one(
    state="Customer requests a refund.",
    questions={
        "route": {
            "type": "choice",
            "instructions": "Which team should handle this?",
            "criteria": {"billing": "Payments and refunds", "technical": "Product faults"},
        },
        "priority": {
            "type": "score",
            "instructions": "How urgent is this request?",
            "criteria": ["Not urgent", "Soon", "Today", "Immediately"],
        },
    },
)
print(response["answers"]["route"]["choice"], response["answers"]["priority"]["score"])
```

`pipeline("decision", model="vllm-sr/Decision-1.0-Sol-2B", trust_remote_code=True)` accepts the same request body. A malformed question is answered with an `invalid_question` error. The model loads on the first GPU when one is visible, otherwise on the CPU (pass `device="cpu"` or `device="cuda:0"` to choose). On a GPU the backbone runs in BF16 with an FP32 decision head; on the CPU everything runs in FP32. A complete question, its candidates and the state are limited to 16,384 tokens; if a question is longer, every question of the request is answered with a `max_length_exceeded` error and nothing is truncated. [flash-linear-attention](https://github.com/fla-org/flash-linear-attention) speeds up the linear-attention layers on a GPU.

## Serve with vLLM Semantic Router

This repository contains model data and its Transformers loading code. Use the vLLM Semantic Router Decision runtime to load `vllm-sr/Decision-1.0-Sol-2B` and serve Choice, Noul, and Score requests. The serving implementation and its dependencies live in vLLM Semantic Router; this release bundles no serving code. The weights do not depend on a particular accelerator; which hardware can serve them is decided by the runtime. For local inference without a server, see Use with 🤗 Transformers above.

After configuring a compatible Decision endpoint, send a [SystemOne request](https://docs.typesafe.ai/api) (replace the placeholder URL and key):

```bash
curl -X POST 'https://your-decision-endpoint.example/v1/systemone' \
  -H 'Authorization: Bearer YOUR_ENDPOINT_API_KEY' \
  -H 'Content-Type: application/json' \
  --data-raw '{"model":"Decision-1.0-Sol-2B","state":"Customer requests a refund.","questions":{"route":{"type":"choice","instructions":"Which team should handle this?","criteria":{"billing":"Payments and refunds","technical":"Product faults"}}}}'
```

The Hugging Face repository is a model download, not a hosted inference endpoint.

The published model's complete state, question, and candidates have a 16,384-token input limit. See the [evaluation scope](evaluation/EVALUATION.md) for measured conditions.

## Architecture

![Decision decoder architecture](assets/architecture.png)

A causal Qwen3.5 text backbone combines gated linear and full attention. A shared candidate head reads candidate endpoints and the final query vector. The serving runtime schedules questions according to available hardware and request load.

[Candidate head](assets/readout.png) · [Vector architecture](assets/architecture.svg)

Adapted from [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B). It evaluates supplied evidence without live retrieval; confidence does not guarantee correctness. [License](LICENSE) · [Attributions](ATTRIBUTIONS.md).