A Japanese BERT‑based model fine‑tuned on the JGLUE JSTS dataset for semantic similarity scoring—introduced in chapter 5 of “Large Language Model Introduction”—with Colab notebooks, transformers‑pipeline usage, and an Apache 2.0 license.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
1,000
Hugging Face likes
2
Listed
—
Listed since the page was created
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 6,000 |
| Jan 2026 | 4,000 |
| Feb 2026 | 4,000 |
| Mar 2026 | 3,000 |
| Apr 2026 | 3,000 |
| May 2026 | 5,000 |
| Jun 2026 | 4,000 |
| Jul 2026 | 3,000 |
| Aug 2026 | 3,000 |
| Sep 2026 | 4,000 |
| Oct 2026 | 2,000 |
| Nov 2026 | 1,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- bert-finetuned-japanese-sentimentchristian-phu329kFine‑tuned Japanese BERT (cl‑tohoku/bert‑base‑japanese‑v2) on Amazon product reviews for sentiment classification, achieving ~81 % accuracy and 0.73 F1 after 6 epochs with a 2 × 10⁻⁵ learning rate.
- bert-base-japanese-v2-wrime-fine-tunepatrickramos1kA Japanese BERT BASE fine‑tuned on the WRIME dataset predicts 0‑4 intensity scores for eight emotions (joy, sadness, anticipation, surprise, anger, fear, disgust, trust) for writers and readers, with code available, trained in 3 hrs on a K80, achieving about 0.6 MSE for writers and 0.2 MSE for readers.
- japanese-sentiment-analysisjarvisx174kJapanese sentiment analysis model trained on the chABSA dataset, achieving loss 0.0001, accuracy 1.0, and F1 1.0, built with Transformers 4.24.0 and PyTorch 1.12.1+cu113, optimized with Adam (learning rate 2e‑05, 10 epochs, batch size 16) and evaluated via model(inputs).
Resources in similar research fields
- bert-large-japanese-v2tohoku-nlp66kJapanese‑BERT‑Large trained on CC‑100 and Wikipedia, using Unidic‑lite word‑level tokenization with WordPiece subwords and whole‑word masking (24 layers, 1024‑dim hidden, 16 heads, 32k vocab), with pretraining code on cl‑tohoku/bert‑japanese.Shared: Representation Learning・Language Models
- bert-base-japanese-v3tohoku-nlp66kJapanese BERT‑base (12 layers, 768‑dim hidden, 12 heads, 32 k vocab) pretrained with whole‑word masking on CC‑100 and 2023‑Jan Wikipedia, using Unidic 2.1.2 word‑level tokenization plus WordPiece, in 2 M training steps.Shared: Representation Learning・Language Models
bert-japanesecl-tohoku551BERT models for Japanese language text.GitHubShared: Representation Learning・Language Models
Laboro-BERT-Japaneselaboroai73Laboro BERT Japanese: Japanese BERT Pre-Trained With Web-CorpusGitHubShared: Representation Learning・Language Models
language-pretrainingretarfi50BERT and ELECTRA models of PyTorch implementations for Japanese text.GitHubShared: Representation Learning・Language Models
bert-japanese-aozoraakirakubo41Japanese BERT trained on Aozora Bunko and Wikipedia, pre-tokenized by MeCab with UniDic & SudachiPyGitHubShared: Representation Learning・Language Models