Bo-Boundary-mmbert-0.2

Bo-Boundary-mmBERT 0.2

A ModernBERT token classifier fine-tuned to detect text / outline boundaries in Tibetan Buddhist volume text. Each token is labelled B (boundary) or O (non-boundary).

This is the 0.2 release of BDRC/Bo-Boundary-mmBert. Weights are checkpoint-46000 from run run_bo_outline_neg06 (epoch 2 of 3). The run later early-stopped at step 52,000; 46k is the checkpoint that scored highest micro-F1 on the frozen 100-document benchmark after a decoder sweep.

Hosted as BDRC/Bo-Boundary-mmbert-0.2.

Model details

Training data

Prepared from BDRC outline annotations (data/Bo_Outline_neg06). Splits are work-level and stratified by print_format, so volumes of the same BDRC work never appear in more than one split. Mixed-format works keep only majority-format volumes (119 minority-format volumes dropped). There is no test split in the training set — evaluation uses a separately curated 100-document benchmark.

Splits

Stratification by print_format (work-level)

Train label distribution

The boundary class is extremely rare. All windows that contain a B label are kept; only O-only train windows are downsampled at prepare time.

Training

Run directory: output/run_bo_outline_neg06. Started 2026-09-11. The full run early-stopped at step 52,000 after 105 h 42 m (patience = 10 evals with no doc-level F2 gain). This Hub checkpoint is step 46,000.

Hyperparameters

In-loop validation used the production decoder at threshold 0.70. Those numbers are not the benchmark operating point below.

Infrastructure

• GPU: 1 × NVIDIA A100-SXM4-40GB (39.5 GB)
• Time to this checkpoint: ~92 h 55 m (step 46,000)
• Full run: 105 h 42 m (early stop at step 52,000)

Validation at this checkpoint (80 holdout docs, threshold 0.70)

Key in-loop milestones (same 80-doc, threshold-0.70 decoder):

Step 34,000 was the run’s best in-loop F2 (saved as checkpoints/best). Step 46,000 is released here because it generalises better on the frozen benchmark once the decode threshold is swept.

Evaluation on the benchmark

Frozen 100-document outline-boundary benchmark (78 works, 1,643 gold breakpoints, 23.7 M characters). A predicted boundary matches gold if it falls within ±25 characters. Decoder: centre-weighted sliding-window B probabilities → threshold → merge nearby peaks.

Recommended operating point

threshold = 0.55, merge window = 75 characters (best micro-F1 on this checkpoint).

Other useful decode settings

postprocess did not change scores on this sweep.

Source breakdown (threshold 0.70, merge 50)

Print format (threshold 0.70, merge 50)

How to use

from transformers import AutoModelForTokenClassification, AutoTokenizer

repo_id = "BDRC/Bo-Boundary-mmbert-0.2"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForTokenClassification.from_pretrained(repo_id)

Production decode (centre-weighted windows, threshold, 50-char merge) is implemented in the training package:

mmbert-boundary predict input.txt --model BDRC/Bo-Boundary-mmbert-0.2 --threshold 0.55

Or via OpenPecha/outline-detection:

from outline_detection import MmBertDetector

det = MmBertDetector(model_name_or_path="BDRC/Bo-Boundary-mmbert-0.2")
boundaries = det.predict(text)  # [(offset, confidence, "mmbert"), ...]

Recommended defaults for this checkpoint: --threshold 0.55, merge nearby peaks within 75 characters, match gold within ±25 characters. Raise the threshold (0.60–0.70) if you need fewer false positives; lower it (0.45–0.50) if you need higher recall.

Limitations

• Trained on BDRC outline-annotated Tibetan volumes (pering and modern_book). Other layouts, scripts, or OCR engines may degrade.
• Sparse and zero-boundary volumes still produce extra detections. Downstream use should keep a confidence threshold.
• modern_book recall is lower than pering at the high-precision 0.70 setting (0.57 vs 0.82).
• In-loop checkpoint selection used F2 at threshold 0.70 on 80 val docs; published scores use a held-out 100-doc benchmark and a swept decoder.

Credits

Trained for the Buddhist Digital Resource Center (BDRC) etext corpus, with funding from the Khyentse Foundation. Successor to BDRC/Bo-Boundary-mmBert.