Skip to page content
SAVRN
Search Plan a project

Open-weight model · Token classification

bert-base-cased-pos-tagging-ewt

by Angel Rivaldo Canche Chuc Rivaldo2309030/bert-base-cased-pos-tagging-ewt

bert-base-cased-pos-tagging-ewt is an open-weight model for token classification from Angel Rivaldo Canche Chuc, released under Apache License 2.0. It has 108M parameters and a 512-token context. At 16-bit it needs about 0.3 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.

Modelo bert-base-cased ajustado finamente (Fine-tuned) para la tarea de Part-of-Speech (POS) Tagging utilizando las 17 etiquetas universales (UPOS) del dataset universal-dependencies/universaldependencies (configuración enewt).

Parameters108M
Context512
Weights431.0 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve bert-base-cased-pos-tagging-ewt (108M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.2 GB 0.3 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.

bert-base-cased-pos-tagging-ewt on every accelerator the SAVRN Index prices, at every precision

Model Card

By Angel Rivaldo Canche Chuc, published under apache-2.0, revision 10b74a3342c1.

Modelo bert-base-cased ajustado finamente (Fine-tuned) para la tarea de Part-of-Speech (POS) Tagging utilizando las 17 etiquetas universales (UPOS) del dataset universal-dependencies/universaldependencies (configuración enewt). Etiquetado Morfosintáctico Automático: Clasificación de categorías gramaticales (Part-of-Speech Tagging) en oraciones en idioma inglés. Análisis Lingüístico: Extracción de características sintácticas para sistemas downstream de NLP, desambiguación léxica y procesamiento del lenguaje. Parameter Groups (Método 1 - Partial): classifier: Learning Rate 1e-3 bert.encoder.layer.10 y layer.11: Learning Rate 2e-5 Parameter Groups (Método 2 - Full Ganador): classifier…

Read Angel Rivaldo Canche Chuc's full model card

BERT Base Cased - Part-of-Speech (POS) Tagging (en_ewt)

Modelo bert-base-cased ajustado finamente (Fine-tuned) para la tarea de Part-of-Speech (POS) Tagging utilizando las 17 etiquetas universales (UPOS) del dataset universal-dependencies/universal_dependencies (configuración en_ewt).

Resumen del Modelo

  • Desarrollado por: Angel Rivaldo
  • Modelo Base: bert-base-cased (110M parámetros)
  • Tarea: Token Classification (POS Tagging)
  • Idioma: Inglés (en)
  • Dataset: Universal Dependencies v2.14 (en_ewt, 17 UPOS tags)
  • Manejo de Subpalabras: Regla estricta del -100 para subpalabras de continuación (##), [CLS], [SEP] y padding.

Resultados Empíricos Auditar en Test Set

Método de Adaptación Parámetros Entrenables Épocas Accuracy F1-Score (Macro) Precision (Macro) Recall (Macro) Test Loss
Partial Fine-Tuning (Capas 10, 11 + 2 Param Groups) 14.2M (13.17%) 3 95.43% 0.8909 0.8997 0.8865 0.1520
Full Fine-Tuning(5 Épocas + Cosine Scheduler) 107.7M (100%) 5 97.42% 0.9446 0.9536 0.9384 0.1134

Intended Use (Uso Previsto)

Aplicaciones Primarias

  • Etiquetado Morfosintáctico Automático: Clasificación de categorías gramaticales (Part-of-Speech Tagging) en oraciones en idioma inglés.
  • Análisis Lingüístico: Extracción de características sintácticas para sistemas downstream de NLP, desambiguación léxica y procesamiento del lenguaje.

Integración en Python (pipeline)

from transformers import pipeline

pos_tagger = pipeline(
    "token-classification", 
    model="Rivaldo2309030/bert-base-cased-pos-tagging-ewt",
    aggregation_strategy="first"
)

texto = "BERT models achieve state-of-the-art results on NLP tasks."
predicciones = pos_tagger(texto)

for item in predicciones:
    print(f"{item['word']:<15} -> {item['entity_group']}")

Limitations (Limitaciones)

  • Idioma: Restringido al idioma inglés (en). No apto para análisis multilingüe sin un entrenamiento adicional.
  • Longitud de Secuencia: Truncado a max_length = 128 subpalabras. Oraciones excesivamente largas serán cortadas.
  • Dominio: Entrenado sobre el corpus Universal Dependencies en_ewt (que combina blogs, noticias, reviews y correos). Puede presentar una leve degradación de precisión en textos con jerga informal extrema o tweets sin puntuación.

Configuración e Hiperparámetros de Entrenamiento

  • Random Seed: SEED = 42 (reproducibilidad garantizada)
  • Batch Size: 32 por dispositivo
  • Optimizador: AdamW (weight_decay = 0.01)
  • Parameter Groups (Método 1 - Partial):
  • classifier: Learning Rate 1e-3
  • bert.encoder.layer.10 y layer.11: Learning Rate 2e-5
  • Parameter Groups (Método 2 - Full Ganador):
  • classifier: Learning Rate 1e-3
  • bert.encoder: Learning Rate 2e-5 con planificador cosine y warmup_steps = 100

References (Referencias)

  1. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805.
  2. Nivre, J., et al. (2020). Universal Dependencies v2: An Open Community Initiative for Cross-Lingual Dependency Annotation. Computational Linguistics / LREC.
  3. Wolf, T., et al. (2020). Transformers: State-of-the-Art Natural Language Processing. EMNLP 2020.

Configuration

Architecture
BertForTokenClassification
Context length (tokens)
512
Layers
12
Hidden size
768
Feed-forward size
3,072
Attention heads
12
Vocabulary size
28,996
Model type
bert

Identity and Version

Repository
Rivaldo2309030/bert-base-cased-pos-tagging-ewt
Publisher
Angel Rivaldo Canche Chuc
Task
Token classification
Modality
Text
Library
transformers
Parameters
108M parameters
Languages
en
Revision
10b74a3342c1d2e8451d8269f39a6d3ec58d3de7
First published
2026-09-25
Last updated
2026-09-26

Files and Weights

6 files, 431.6 MB in total. The weights are 1 file totalling 431.0 MB in safetensors.

Weights1 file · 431.0 MB
Configuration1 file · 1.4 KB
Tokenizer2 files · 669.5 KB
Documentation1 file · 4.1 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights431.0 MB 387ad1d47ebc
config.jsonConfiguration1.4 KB —
README.mdDocumentation4.1 KB —
.gitattributesRepository1.5 KB —
tokenizer.jsonTokenizer669.0 KB —
tokenizer_config.jsonTokenizer478 B —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
431.0 MB
Download from Angel Rivaldo Canche Chuc

Released by Angel Rivaldo Canche Chuc through its official repository on Hugging Face. Read the license.

Built From

  • Described by arXiv:1810.04805
  • Trained on (disclosed) universal-dependencies/universal_dependencies

Memory Requirements

PrecisionWeights in memory
As published431.0 MB
16-bit0.2 GB
8-bit0.1 GB
4-bit0.1 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About bert-base-cased-pos-tagging-ewt

How much GPU memory does bert-base-cased-pos-tagging-ewt need?

About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (108M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run bert-base-cased-pos-tagging-ewt on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use bert-base-cased-pos-tagging-ewt commercially?

Yes. bert-base-cased-pos-tagging-ewt is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

What is bert-base-cased-pos-tagging-ewt's context length?

512 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Token classification

OpenMed-NER-OrganismDetect-BioPatient-108M

OpenMed

Specialized model for Species Entity Recognition - Species names from the Species-800 dataset This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for species entity recognition - species names from the species-800 dataset. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as drug interaction detection, medication extraction from patient records, adverse event monitoring, literature mining for drug discovery, and biomedical knowledge graph construction with production-ready reliability for clinical and research…

Open weights apache-2.0 108M parameters 512 tokens transformers
View model

Model · Token classification

bert-base-NER

D

If my open source models have been useful to you, please consider supporting me in building small, useful AI models for everyone (and help me afford med school / help out my parents financially). Thanks! bert-base-NER is a fine-tuned BERT model that is ready to use for Named Entity Recognition and achieves state-of-the-art performance for the NER task. It has been trained to recognize four types of entities: location (LOC), organizations (ORG), person (PER) and Miscellaneous (MISC). Specifically, this model is a bert-base-cased model that was fine-tuned on the English version of the standard CoNLL-2003 Named Entity Recognition dataset. If you'd like to use a larger BERT-large model…

Open weights mit 108M parameters 512 tokens transformers
View model

This model is a fine-tuned version of syssec-utd/py314-pylingual-v11-mlm on the syssec-utd/segmentation-py314-pylingual-v11-tokenized dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 2e-05 - trainbatchsize: 64 - evalbatchsize: 8 - distributedtype: multi-GPU - numdevices: 3 - totaltrainbatchsize: 192 - totalevalbatchsize: 24 - lrschedulertype: linear - numepochs: 2 - mixedprecisiontraining: Native AMP - Transformers 5.17.0 - Pytorch 2.14.0+cu130 - Datasets 5.0.1 - Tokenizers 0.23.2

Open weights 109M parameters 1,026 tokens transformers
View model

Model · Token classification

OpenMed-NER-AnatomyDetect-ElectraMed-109M

OpenMed

Specialized model for Anatomical Entity Recognition - Anatomical structures and body parts This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for anatomical entity recognition - anatomical structures and body parts. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as drug interaction detection, medication extraction from patient records, adverse event monitoring, literature mining for drug discovery, and biomedical knowledge graph construction with production-ready reliability for clinical and research applications.…

Open weights apache-2.0 109M parameters 512 tokens transformers
View model

Model · Token classification

OpenMed-NER-SpeciesDetect-ElectraMed-109M

OpenMed

Specialized model for Species Entity Recognition - Species and organism names This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for species entity recognition - species and organism names. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as drug interaction detection, medication extraction from patient records, adverse event monitoring, literature mining for drug discovery, and biomedical knowledge graph construction with production-ready reliability for clinical and research applications. This model can identify and…

Open weights apache-2.0 109M parameters 512 tokens transformers
View model

Model · Token classification

OpenMed-NER-GenomicDetect-PubMed-109M

OpenMed

Specialized model for Gene Entity Recognition - Gene-related entities This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for gene entity recognition - gene-related entities. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as drug interaction detection, medication extraction from patient records, adverse event monitoring, literature mining for drug discovery, and biomedical knowledge graph construction with production-ready reliability for clinical and research applications. This model can identify and classify the…

Open weights apache-2.0 109M parameters 512 tokens transformers
View model