esupar included

README.md

@@ -5,6 +5,7 @@ tags:
 - "serbian"
 - "token-classification"
 - "pos"
+- "dependency-parsing"
 base_model: jerteh/gpt2-vrabac
 datasets:
 - "universal_dependencies"
@@ -19,7 +20,7 @@ widget:
 
 ## Model Description
 
-This is a GPT-2 model in Serbian (Cyrillic and Latin) for POS-tagging, derived from [gpt2-vrabac](https://huggingface.co/jerteh/gpt2-vrabac). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
+This is a GPT-2 model in Serbian (Cyrillic and Latin) for POS-tagging and dependency-parsing, derived from [gpt2-vrabac](https://huggingface.co/jerteh/gpt2-vrabac). 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
 
@@ -28,3 +29,14 @@ from transformers import pipeline
 nlp=pipeline("upos","KoichiYasuoka/gpt2-small-serbian-upos",trust_remote_code=True,aggregation_strategy="simple")
 ```
 
+or
+
+```py
+import esupar
+nlp=esupar.load("KoichiYasuoka/gpt2-small-serbian-upos")
+```
+
+## See Also
+
+[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa/GPT models
+

supar.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b48aef483c9714b9657efc7724c8423088407655138b460fef96b5ca899a55d
+size 548477506