---
language:
- "th"
tags:
- "thai"
- "token-classification"
- "pos"
- "dependency-parsing"
base_model: KoichiYasuoka/modernbert-base-thai-wikipedia
datasets:
- "universal_dependencies"
license: "apache-2.0"
pipeline_tag: "token-classification"
widget:
- text: "หลายหัวดีกว่าหัวเดียว"
---

# modernbert-base-thai-wikipedia-upos

## Model Description

This is a ModernBERT model pre-trained on Thai Wikipedia texts for POS-tagging and dependency-parsing, derived from [modernbert-base-thai-wikipedia](https://huggingface.co/KoichiYasuoka/modernbert-base-thai-wikipedia). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).

## How to Use

```py
from transformers import pipeline
nlp=pipeline("upos","KoichiYasuoka/modernbert-base-thai-wikipedia-upos",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("หลายหัวดีกว่าหัวเดียว"))
```

or

```py
import esupar
nlp=esupar.load("KoichiYasuoka/modernbert-base-thai-wikipedia-upos")
print(nlp("หลายหัวดีกว่าหัวเดียว"))
```

## See Also

[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa/GPT models