---
license: cc-by-nc-sa-4.0
base_model: Qwen/Qwen3.5-9B
base_model_relation: adapter
tags:
  - multimodal
  - vision
  - decision-model
  - lora
  - qwen3_5
---

# Jolt-9B

![Jolt Logo](https://huggingface.co/mlengineer-ai/Jolt-9B/resolve/main/jolt.png)

Jolt-9B is a multimodal decision model. Given text or an image and a set of
candidate answers, it returns candidate probabilities, a truth estimate, or an
ordered score. It does not generate free-form answers.

## Model details

| Property | Value |
| --- | --- |
| Base model | [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) |
| Base revision | `c202236235762e1c871ad0ccb60c8ee5ba337b9a` |
| Checkpoint | L2, seed 42, selected at update 3,600 |
| Development macro accuracy | 85.31% (checkpoint selection partition) |
| Training objective | Direct-composite loss |
| Training precision | BF16 base |
| Trainable weights | Rank-8 language LoRA and a linear candidate scorer |
| Input | Text, or text plus one decoded image |
| Limits | 2–128 candidates per question; 4,096-token inference limit |

The reported development score selected the checkpoint within its run. It is not
an independent test score. Test data were not used to select this checkpoint.

### Local evaluation results

| Held-out test lane | Dataset macro | Row weighted |
| --- | ---: | ---: |
| Text · 18 datasets | 85.81% | 86.55% |
| Images · 8 datasets | 84.88% | 97.51% |
| All · 26 datasets | 85.52% | 94.08% |

JevBench v1.2.2 public subset: **182/231** (78.79% pooled; 84.96% tier-balanced). The public subset contains 231 tasks; 303 official tasks were unavailable. This is a single checkpoint, seed 42, selected at update 3,600. Unit temperatures were used; no post-training temperature fit was applied.

### JevBench

![JevBench](https://huggingface.co/mlengineer-ai/Jolt-9B/resolve/main/jevbench.png)

### 18 text dataset benchmarks

![TextBench](https://huggingface.co/mlengineer-ai/Jolt-9B/resolve/main/text_bench.png)

### 8 image dataset benchmarks

![ImageBench](https://huggingface.co/mlengineer-ai/Jolt-9B/resolve/main/image_bench.png)

You can find a comprehensive model comparison report at: *model_comparison_dashboard.html*

## Use

This repository contains the compact Jolt adapter and inference source. It does
not duplicate Qwen's base weights: the runtime downloads the pinned public Qwen
revision on first use and caches it locally. The adapter format is Jolt's custom
decision-model format, so load it with the included runtime rather than
`AutoModel.from_pretrained`.

The runtime currently requires Python 3.12+, a CUDA-enabled PyTorch setup, and a
CUDA GPU. From a clone or downloaded copy of this repository:

```bash
python -m pip install -r requirements-cuda.txt
python -m pip install -e . --no-deps
```

Then:

```python
from jolt.predictor import Predictor

model = Predictor.from_checkpoint("mlengineer-ai/Jolt-9B")
result = model.predict(
    {"message": "I was charged twice. Please refund the duplicate."},
    {
        "route": {
            "type": "choice",
            "instructions": "Which team should handle this request?",
            "criteria": ["billing", "technical support", "sales"],
        },
        "refund": {
            "type": "noul",
            "instructions": "Is a refund requested?",
        },
    },
)

print(result["answers"]["route"]["choice"])
print(result["answers"]["refund"]["noul"])
```

For an image question, pass a decoded PIL image as `state["image"]`. This
example uses the `model` loaded above:

```python
from PIL import Image

image = Image.open("path/to/image.jpg").convert("RGB")
image_result = model.predict(
    {"image": image, "question": "Which animal is shown?"},
    {
        "animal": {
            "type": "choice",
            "instructions": "Identify the animal in the image.",
            "criteria": ["cat", "dog", "bird", "other"],
        }
    },
)

print(image_result["answers"]["animal"]["choice"])
```

## Training and data

Jolt follows the recipe based on the [Dohnuts](https://huggingface.co/PsiACE/Dohnuts-0.1.0-0.8B) project. These checkpoints start from the
Qwen3.5 base model listed above; they do not use Dohnuts model weights as their
base. Jolt trained rank-8 LoRA weights and a candidate scorer with the base
model frozen. Jolt's public-data task suite and split design are adapted from
Dohnuts. Its [data reference](https://github.com/PsiACE/dohnuts/blob/main/docs/data-and-evaluation.md)
lists source datasets and their known terms. The adapter metadata records
fingerprints for Jolt's training and development partitions. Training data are
not included here.

## Model variations

* https://huggingface.co/mlengineer-ai/Jolt-0.8B
* https://huggingface.co/mlengineer-ai/Jolt-2B
* https://huggingface.co/mlengineer-ai/Jolt-4B
* https://huggingface.co/mlengineer-ai/Jolt-9B

## Licensing

This release offers the adapter and decision-head weights under CC BY-NC-SA 4.0;
see `LICENSE`. For this prepared release, this conservative default follows the
original Dohnuts model release. It is not a legal determination that every source
dataset's terms necessarily apply to trained weights. The training mixture
includes sources with different terms, including
[ScienceQA](https://github.com/lupantech/ScienceQA/blob/main/README.md), whose
maintainers specify CC BY-NC-SA 4.0 for the dataset. The available records do
not establish commercial clearance for these trained weights; review the source
dataset terms before use.

The bundled inference source is adapted from Dohnuts and is licensed under
Apache-2.0; see `LICENSE-CODE` and `NOTICE-CODE`. The Qwen base model is
separately licensed by its publisher under Apache-2.0. Those licenses do not
replace or change the terms of training data.