| --- |
| license: apache-2.0 |
| library_name: transformers |
| pipeline_tag: token-classification |
| base_model: answerdotai/ModernBERT-base |
| tags: |
| - ner |
| - on-device |
| - privacy |
| - flowx |
| - openner |
| - logistics |
| - de-identification |
| - token-classification |
| metrics: |
| - f1 |
| --- |
| |
| # BoLParse |
|
|
| **BoLParse** is a small, on-device logistics NER model from the FlowX **OpenNER** family. Developed by **FlowX.AI**. Runs 100% on-premise / air-gapped, so no data leaves your boundary. |
|
|
| ## What it does |
| - **Task:** token-classification |
| - **Base model:** `answerdotai/ModernBERT-base` |
| - **Entity types (6):** BL_NO, CARGO, CONSIGNEE, CONTAINER_NO, PORT, SHIPPER |
| - **Held-out F1:** 1.0000 |
| - **Runtime:** CPU, Apple Silicon, one GPU, or browser/edge via ONNX (INT8). ~100-160 ms/doc on CPU. |
|
|
| ## Why a small model |
| Fine-tuned encoders match or beat frontier LLMs on structured, convention-bound extraction, at a fraction of the latency and cost, with **zero data egress**. Identifiers are validated by checksum (IBAN mod-97, card Luhn, ISIN/LEI, container ISO-6346, VIN, national IDs), a correctness guarantee general LLMs lack. See the FlowX OpenNER benchmark for measured results. |
|
|
| ## Usage |
| ```python |
| from transformers import AutoTokenizer, AutoModelForTokenClassification |
| tok = AutoTokenizer.from_pretrained("flowxai/bolparse") |
| model = AutoModelForTokenClassification.from_pretrained("flowxai/bolparse") |
| ``` |
|
|
| ## License & attribution |
| Licensed under the **Apache License 2.0**. Copyright 2026 **FlowX.AI** (https://flowx.ai). See the `NOTICE` file. Trained on synthetic, checksum-validated data. |
|
|
| _Part of the FlowX OpenNER model family. Synthetic-data F1 reflects an in-distribution synthetic distribution; validate on real documents before production use._ |
