metadata
language:
- en
license: apache-2.0
library_name: transformers
tags:
- transformers
- modernbert
- fill-mask
- masked-language-model
pipeline_tag: fill-mask
datasets:
- mjbommar/ogbert-v1-mlm
model-index:
- name: ogbert-2m-base
results:
- task:
type: word-similarity
dataset:
name: SimLex-999
type: simlex999
metrics:
- type: spearman
value: 0.162
OGBert-2M-Base
A tiny (2.1M parameter) ModernBERT-based masked language model for glossary and domain-specific text.
Related models:
- mjbommar/ogbert-2m-sentence - Sentence embedding version with mean pooling + L2 normalization
Model Details
| Property | Value |
|---|---|
| Architecture | ModernBERT |
| Parameters | 2.1M |
| Hidden size | 128 |
| Layers | 4 |
| Attention heads | 4 |
| Vocab size | 8,192 |
| Max sequence | 1,024 tokens |
Training
- Task: Masked Language Modeling (MLM)
- Dataset: mjbommar/ogbert-v1-mlm - derived from OpenGloss, a synthetic encyclopedic dictionary with 537K senses across 150K lexemes
- Masking: Standard 15% token masking
Performance
Word Similarity (SimLex-999)
SimLex-999 measures Spearman correlation between model cosine similarities and human judgments on 999 word pairs. Higher = better alignment with human perception of word similarity.
| Model | Params | SimLex-999 (ρ) |
|---|---|---|
| OGBert-2M-Base | 2.1M | 0.162 |
| BERT-base | 110M | 0.070 |
| RoBERTa-base | 125M | -0.061 |
OGBert-2M-Base achieves 2.3x better word similarity than BERT-base with 52x fewer parameters.
Usage
Fill-Mask Pipeline
from transformers import pipeline
fill_mask = pipeline('fill-mask', model='mjbommar/ogbert-2m-base')
result = fill_mask('The financial <|mask|> was approved.')
Output:
| Rank | Token | Score |
|---|---|---|
| 1 | report | 0.031 |
| 2 | transaction | 0.025 |
| 3 | system | 0.021 |
| 4 | audit | 0.019 |
| 5 | account | 0.017 |
Direct Model Usage
from transformers import AutoModelForMaskedLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('mjbommar/ogbert-2m-base')
model = AutoModelForMaskedLM.from_pretrained('mjbommar/ogbert-2m-base')
inputs = tokenizer('The <|mask|> definition is clear.', return_tensors='pt')
outputs = model(**inputs)
For Sentence Embeddings
Use mjbommar/ogbert-2m-sentence instead, which includes mean pooling and L2 normalization for optimal similarity search.
Citation
If you use this model, please cite the OpenGloss dataset:
@article{bommarito2025opengloss,
title={OpenGloss: A Synthetic Encyclopedic Dictionary and Semantic Knowledge Graph},
author={Bommarito II, Michael J.},
journal={arXiv preprint arXiv:2511.18622},
year={2025}
}
License
Apache 2.0