Usage
See inference_example.py and prompt_template.txt.
- Message order:
[image BEFORE, image AFTER, prompt text].
- Images: 960x540 (
min_pixels = max_pixels = 960*540). One slide point = one pixel for a 16:9 deck.
- Greedy decoding, default chat template.
Training
Table | |
|---|
| Base | Qwen3.5-9B, bf16 |
| Adapter | LoRA, r 16, alpha 32, on the language model and the vision encoder |
| Data | 7,260 training samples (plus 374 for validation) with human-confirmed labels, from publicly licensed decks (CC0 / CC-BY) |
Evaluation
Held-out set of 750 samples from decks not seen in training:
Table with columns: Metric, Value| Metric | Value |
|---|
| Verdict accuracy, edits without a repair (n=497) | 0.932 (base model: 0.60) |
| Verdict accuracy, all 750 samples | 0.955 |
| Defect precision / recall / F1, all 750 samples | 0.963 / 0.954 / 0.959 |
| Repair targets the right shapes with a permitted tool, all 750 samples | 0.948 |
License
Apache-2.0, following the base model.