# lilt-only-base

Layout-only pretrained checkpoint from the official [LiLT repository](https://github.com/jpwang/lilt).

This is **not a complete model** — it contains only the 2D spatial (layout) encoder, with no text encoder. It is intended as a building block for combining with any RoBERTa-like text encoder.

## What is this?

LiLT (Language-Independent Layout Transformer) decouples text and layout understanding into two separate encoders. `lilt-only-base` contains exclusively the **layout encoder** weights, pretrained on document layout understanding (IIT-CDIP dataset).

This allows combining it with any RoBERTa-compatible text encoder to produce a language-specific document understanding model.

## Usage

Use [`gen_weight_roberta_like.py`](https://github.com/jpwang/lilt) from the official repository to combine with your text encoder of choice:

```bash
python gen_weight_roberta_like.py \
     --lilt lilt-only-base/pytorch_model.bin \
     --text your-roberta-model/pytorch_model.bin \
     --config your-roberta-model/config.json \
     --out lilt-your-language-base
```

Compatible text encoders: any RoBERTa-like model (`roberta-base`, `camembert-base`, `microsoft/infoxlm-base`, etc.)

## Files

| File | Description |
|------|-------------|
| `model.safetensors` | Layout encoder weights (safetensors format) |
| `pytorch_model.bin` | Layout encoder weights (PyTorch format) |
| `config.json` | Model configuration (`model_type: liltrobertalike`) |

## Note on model type

This checkpoint uses `model_type = liltrobertalike`, a custom type defined in the original LiLT repository. It cannot be loaded directly with `AutoModel` from HuggingFace transformers without first combining it with a text encoder via the procedure above.

## License

MIT — following the original [jpwang/lilt](https://github.com/jpwang/lilt) repository.

## Acknowledgements

- [LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding](https://arxiv.org/abs/2202.13669) — Wang et al., 2022
- Original weights: [jpwang/lilt](https://github.com/jpwang/lilt)

> **Note**: This is not an official HuggingFace release from the original authors.