README.md

---
base_model: Qwen/Qwen3.6-35B-A3B
library_name: peft
pipeline_tag: image-text-to-text
license: apache-2.0
tags:
- base_model:adapter:Qwen/Qwen3.6-35B-A3B
- peft
- lora
- document-ai
- form-understanding
- table-structure-recognition
- synthetic-data
---

# FormStruct-Bench-SFT

FormStruct-Bench-SFT is a PEFT LoRA adapter for
[`Qwen/Qwen3.6-35B-A3B`](https://huggingface.co/Qwen/Qwen3.6-35B-A3B).
It is fine-tuned on synthetic FormStruct training data for structured form
understanding from document images.

## Loading

```python
import torch
from peft import PeftModel
from transformers import AutoModelForImageTextToText, AutoProcessor

base_id = "Qwen/Qwen3.6-35B-A3B"
adapter_id = "D2I-CUHK-Shenzhen/FormStruct-Bench-SFT"

processor = AutoProcessor.from_pretrained(adapter_id, trust_remote_code=True)
base_model = AutoModelForImageTextToText.from_pretrained(
    base_id,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)
model = PeftModel.from_pretrained(base_model, adapter_id)
model.eval()
```

## License

Apache-2.0, following the base model license. See `LICENSE`.