| --- |
| library_name: transformers |
| pipeline_tag: text-classification |
| tags: |
| - bert |
| - document-processing |
| - table-selection |
| - lhdn |
| - ebc |
| --- |
| |
| # LHDN Table Classifier · BERT · Production Snapshot |
|
|
| A production snapshot of the acceler-technology team's BERT classifier for LHDN table-related text. It preserves released model and tokenizer files separately from the development checkpoint. |
|
|
| **中文简介：** 团队 BERT 表格相关文本分类模型的生产快照，保存独立于开发仓库的发布版本。 |
|
|
| ## Purpose and model details |
|
|
| The model predicts a class from input text for the team's table-selection work. It does not directly read document images, detect table boundaries, or extract individual cells. |
|
|
| | Item | Value | |
| | --- | --- | |
| | Role | Production snapshot | |
| | Architecture | `BertForSequenceClassification` | |
| | Recorded source | `acceler-technology/dev-lhdn-table-bert-model` | |
| | Task setting | Single-label classification | |
| | Encoder layers / hidden size | 12 / 768 | |
| | Maximum input positions | 512 | |
| | Tokenizer | Lowercasing `BertTokenizer` | |
| | Saved Transformers version | 4.48.2 | |
|
|
| Sources: [config.json](https://huggingface.co/acceler-technology/prod-lhdn-table-bert-model/blob/main/config.json) and the saved tokenizer configuration. Use this repository's tokenizer with its weights. Confirm the training label map before interpreting predictions. The `prod` name identifies a release snapshot; it does not establish a current live deployment. |
|
|
| ## Load the model |
|
|
| Install `torch` and `transformers` first. |
|
|
| ```python |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification |
| |
| model_id = "acceler-technology/prod-lhdn-table-bert-model" |
| tokenizer = AutoTokenizer.from_pretrained(model_id) |
| model = AutoModelForSequenceClassification.from_pretrained(model_id) |
| model.eval() |
| ``` |
|
|
| This example loads the saved artifacts. Input preparation must match training. Long text needs a chunking or truncation policy within the 512-position limit. |
|
|
| ## Project and limitations |
|
|
| Related project data is held in [lhdn-dataset](https://huggingface.co/datasets/acceler-technology/lhdn-dataset), which remains private. The exact training subset, full recipe, and quantitative evaluation results are not documented here. |
|
|
| Unfamiliar documents and text-extraction errors can change classification results. Review predictions before downstream use. The model does not determine tax or legal outcomes. |
|
|
| ## Team and links |
|
|
| Developed within [acceler-technology](https://huggingface.co/acceler-technology). Henry ([HenryTeo27](https://huggingface.co/HenryTeo27)) led this project area, executed the data work, and participated in model training and technical discussions. [kwyong](https://huggingface.co/kwyong) handled model uploads. |
|
|
| [Project showcase](https://github.com/HenryTeo27/EBC-HuggingFace-Showcase) · [Development BERT model](https://huggingface.co/acceler-technology/dev-lhdn-table-bert-model) |
|
|
| A license has not been specified for this checkpoint. Public visibility alone does not grant unrestricted reuse rights. |
|
|
