belumind/barb-1-ie-vi
token-classification model by belumind
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Joint entity and relation extraction for Vietnamese. The strongest model we have built on every text condition we measure - clean prose, text with the diacritics stripped, and ALL CAPS - by a wide margin. The earlier models are the goby line (ca bong) - goby-4, goby-7, goby-9, goby-12 - and they stay where they are, under those names. This one starts a new line: a barb (ca ho, the giant Mekong carp) is a considerably larger fish, and this is a considerably stronger model. The goby line remains useful and goby-12 is still the one to reach for on job-title boundaries. Two things, both of which turned out to matter more than any hyperparameter we tried: were initialized from goby-1, which carried habits learned on an uncleaned dataset. 5,824 clean sentences kept in full, plus 3,784 degraded copies (30% diacritics stripped, 20% lowercased, 15% uppercased). Earlier versions replaced clean…
Read the full model card ↗ · Preview checked 2026-09-21T07:10:39.921Z
Inside the original model card — Document outline
- barb-1-ie-vi
- What changed
- Results
- Known limitations
- Usage
- Two things that silently cost you a lot of accuracy
- Which model do I want?
- Related
- Citation
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
belumind/barb-1-ie-vi is a token-classification model repository published by belumind on Hugging Face. The source reports the gliner library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- token-classification
- Library
- gliner
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 466,576,896
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-21T06:21:01.000Z
- Last modified
- 2026-09-21T06:36:46.000Z
Compatibility and lineage
Reported languages: vi
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-21T06:36:48.800Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
joseeangel/bert-base-uncased-conll2003-ner