Japanese‑Roberta‑Base is a pretrained masked‑language model from rinna Co., Ltd., with guidelines for proper loading, token preprocessing, position‑id handling, and usage examples emphasizing the need for a leading [CLS] token and consistent tokenization.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
9,000
Hugging Face likes
40
Listed
—
Listed since the page was created
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 9,000 |
| Jan 2026 | 11,000 |
| Feb 2026 | 10,000 |
| Mar 2026 | 12,000 |
| Apr 2026 | 7,000 |
| May 2026 | 158,000 |
| Jun 2026 | 2,000,000 |
| Jul 2026 | 2,000,000 |
| Aug 2026 | 10,000 |
| Sep 2026 | 10,000 |
| Oct 2026 | 8,000 |
| Nov 2026 | 9,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- bert-base-japanese-whole-word-maskingtohoku-nlp462kJapanese BERT‑base pretrained on 2019 Japanese Wikipedia with IPA‑dictionary and whole‑word masking, 12‑layer 768‑dim, 32,000‑vocab, 512‑token sequences, 1 M steps, available at cl‑tohoku/bert‑japanese under CC‑BY‑SA.
- deberta-v2-large-japanese-char-wwmku-nlp76kJapanese DeBERTa V2 large model trained on 171 GB of Japanese Wikipedia, CC‑100, and OSCAR with character‑level sentencepiece tokenization and whole‑word masking, ready for downstream fine‑tuning through Hugging Face Transformers.
- bert-base-japanese-char-v2tohoku-nlp55kA BERT‑base Japanese model (12 layers, 768‑dim hidden states, 12 heads) trained on 30 M Wikipedia sentences (~4 GB) with Unidic 2.1.2 word‑level tokenization followed by character‑level tokenization and whole‑word masking, using 512‑token sequences, 256 batches, and 1 M training steps.
- modernbert-ja-310msbintuitions36kModernBERT‑Ja‑310M is a Japanese‑language BERT variant that blends local‑global attention with RoPE, trained on 4.09 T tokens of Japanese/English text, supports a 102 400‑word vocabulary, 8 192‑token sequences, and is optimized for Flash Attention 2.
- deberta-v2-base-japanese-char-wwmku-nlp24kA Japanese DeBERTa‑V2 base model pre‑trained on 171 GB of Japanese Wikipedia, CC‑100, and OSCAR text with character‑level tokenization, whole‑word masking, trained for 20 days on 8 A100 GPUs, and ready for downstream fine‑tuning.
- deberta-v2-base-japaneseku-nlp24kJapanese DeBERTa V2 base model pretrained on 171 GB of Japanese Wikipedia, CC‑100 and OSCAR data using Juman++ segmentation and SentencePiece tokenization, trained for three weeks on eight NVIDIA A100 GPUs and ready for fine‑tuning.
Resources in similar research fields
- bert-base-japanese-char-v3tohoku-nlp130kJapanese‑language BERT‑Base (12 layers, 768‑dim, 12 heads) pretrained with Unidic‑based word‑level plus character‑level tokenization and whole‑word masking on CC‑100 and 2023 Wikipedia, producing a 7,027‑token vocabulary.Shared: Syntactic Text Processing・Text Segmentation
- bert-base-japanese-chartohoku-nlp11kA BERT‑base Japanese model (12 layers, 768‑dim hidden, 12 heads) pretrained on ~17 M sentences from Japanese Wikipedia (2.6 GB) using MeCab IPA word‑level tokenization followed by character tokenization into a 4000‑word vocabulary, with training code at cl‑tohoku/bert‑japanese and released under CC BY‑SA 3.0.Shared: Syntactic Text Processing・Text Segmentation
- bert-base-japanese-v2tohoku-nlp9kJapanese BERT‑base (12 layers, 768 hidden, 12 heads) pretrained on 4 GB of Japanese Wikipedia (≈30 M sentences) with Unidic 2.1.2 word‑level tokenization, WordPiece sub‑tokenization, and whole‑word masking.Shared: Syntactic Text Processing・Text Segmentation
- bert-base-japanesetohoku-nlp9kA BERT base model pretrained on ~17 M Japanese Wikipedia sentences (2.6 GB) that tokenizes with the IPA dictionary and WordPiece, has 12 layers/768‑dim hidden states/12 heads, a 32 000‑token vocabulary, was trained for 1 M steps on Cloud TPUs and is released under CC‑BY‑SA 3.0.Shared: Syntactic Text Processing・Text Segmentation
- deberta-v2-tiny-japaneseku-nlp14kJapanese DeBERTa V2 tiny, pretrained on ~171 GB of Japanese Wikipedia, CC‑100, and OSCAR corpora, requires Juman++ word segmentation, was trained in 33 h on 8 NVIDIA A100 GPUs, and can be fine‑tuned for downstream tasks.Shared: Syntactic Text Processing・Language Models
rinna_gpt-neox_ggml-lorayukaryavka19The repository contains scripts and merge scripts that have been modified to adapt an Alpaca-Lora adapter for LoRA tuning when assuming the use of the "rinna/japanese-gpt-neox..." [gpt-neox] model converted to ggml.GitHubShared: Syntactic Text Processing・Language Models