KoichiYasuoka
commited on
Commit
•
7c2dad0
1
Parent(s):
ffedd38
initial release
Browse files
README.md
CHANGED
@@ -1,3 +1,29 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- "ja"
|
4 |
+
tags:
|
5 |
+
- "japanese"
|
6 |
+
- "token-classification"
|
7 |
+
- "pos"
|
8 |
+
datasets:
|
9 |
+
- "universal_dependencies"
|
10 |
+
license: "llama2"
|
11 |
+
pipeline_tag: "token-classification"
|
12 |
+
widget:
|
13 |
+
- text: "国境の長いトンネルを抜けると雪国であった。"
|
14 |
---
|
15 |
+
|
16 |
+
# Swallow-7b-plus-upos
|
17 |
+
|
18 |
+
## Model Description
|
19 |
+
|
20 |
+
This is a LLaMA model for POS-tagging, derived from [Swallow-7b-plus-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-plus-hf). Every short-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
|
21 |
+
|
22 |
+
## How to Use
|
23 |
+
|
24 |
+
```py
|
25 |
+
from transformers import pipeline
|
26 |
+
nlp=pipeline("upos","KoichiYasuoka/Swallow-7b-plus-upos",trust_remote_code=True,aggregation_strategy="simple")
|
27 |
+
print(nlp("国境の長いトンネルを抜けると雪国であった。"))
|
28 |
+
```
|
29 |
+
|