Downloads · 30 days
46
14% of all-time downloads
masato12/bert-base-japanese-v3-marc_ja
bert-base-japanese-v3-marc_ja is a text classification model from masato12. Use it when you need a label for a piece of text. It is set up for Transformers PHP. The card lists the license as apache-2.0.
https://huggingface.co/llm-book/bert-base-japanese-v3-marcja with ONNX weights to be compatible with Transformers PHP
Downloads · 30 days
46
14% of all-time downloads
All-time downloads
329
Public
Repo size
558 MB
Likes
1
Public
Click a slice to open those files.
.onnx558 MB · 100%
From the Hugging Face model README
https://huggingface.co/llm-book/bert-base-japanese-v3-marc_ja with ONNX weights to be compatible with Transformers PHP
「大規模言語モデル入門」の第5章で紹介している(感情分析)のモデルです。 cl-tohoku/bert-base-japanese-v3をJGLUEのMARC-jaデータセットでファインチューニングして構築されています。
from transformers import pipeline
text_classification_pipeline = pipeline(model="llm-book/bert-base-japanese-v3-marc_ja")
print(text_classification_pipeline("世界には言葉がわからなくても感動する音楽がある。")[0])
# {'label': 'positive', 'score': 0.9993619322776794}
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).