Instructions to use iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1") model = AutoModelForMaskedLM.from_pretrained("iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| language: | |
| - ja | |
| license: mit | |
| library_name: transformers | |
| pipeline_tag: fill-mask | |
| tags: | |
| - mirei | |
| - modernbert | |
| - masked-lm | |
| - pretraining | |
| base_model: iamtatsuki05/ModernBERT-JP-0.5B-init | |
| datasets: | |
| - hotchpotch/fineweb-2-edu-japanese | |
| # ModernBERT-JP-0.5B-PT-stage1 | |
| [English](README.md) / Japanese | |
| ## Overview | |
| ModernBERT-JP-0.5B-PT-stage1 は、[iamtatsuki05/ModernBERT-JP-0.5B-init](https://huggingface.co/iamtatsuki05/ModernBERT-JP-0.5B-init) を [hotchpotch/fineweb-2-edu-japanese](https://huggingface.co/datasets/hotchpotch/fineweb-2-edu-japanese) で学習した非埋め込みパラメータが約 0.5B パラメータの日本語の ModernBERT モデルです。 最大 1,024 トークンで 10B トークン学習させました。 | |
| - **[Hugging Face Collection](https://huggingface.co/collections/iamtatsuki05/mirei)** | |
| - **[GitHub](https://github.com/iamtatsuki05/MIREI)** | |
|  | |
| ## Usage | |
| ### Requirements | |
| ``` | |
| transformers>=4.51.0 | |
| accelerate>=1.6.0 | |
| sentencepiece>=0.2.0 | |
| flash-attn>=2.7.3 | |
| ``` | |
| ### Sample Code | |
| ```python | |
| import torch | |
| from transformers import AutoModelForMaskedLM, AutoTokenizer | |
| model_name = "iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1" | |
| model_kwargs = { | |
| "torch_dtype": torch.bfloat16, | |
| "attn_implementation": "flash_attention_2", | |
| "device_map": "auto", | |
| } | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForMaskedLM.from_pretrained(model_name, **model_kwargs) | |
| text = f"ハチワレは{tokenizer.mask_token}のキャラクターです。" | |
| inputs = tokenizer(text, return_tensors="pt").to(model.device) | |
| outputs = model(**inputs) | |
| masked_index = inputs["input_ids"][0].tolist().index(tokenizer.mask_token_id) | |
| print(tokenizer.decode(outputs.logits[0, masked_index].argmax(axis=-1))) | |
| ``` | |
| ## Model Details | |
| - **ベースモデル:** [iamtatsuki05/ModernBERT-JP-0.5B-init](https://huggingface.co/iamtatsuki05/ModernBERT-JP-0.5B-init) | |
| - **アーキテクチャ:** ModernBERT | |
| - **最大シーケンス長:** 8,192トークン | |
| - **埋め込み次元:** 1280 | |
| - **トークナイザ:** SentencePiece / 語彙数 102,400 | |
| - **位置エンコーディング:** RoPE | |
| - **対応言語:** 日本語 | |
| ## Model Series | |
| 初期化済みモデルに対して [hotchpotch/fineweb-2-edu-japanese](https://huggingface.co/datasets/hotchpotch/fineweb-2-edu-japanese) で最大 1,024 トークンを約 10B トークン分事前学習したモデル群です。 | |
| | ID | Architecture | #Param. | #Param.<br>w/o Emb. | | |
| |:-:|:-:|:-:|:-:| | |
| | [iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1](https://huggingface.co/iamtatsuki05/ModernBERT-JP-0.5B-PT-stage1)<br>(this model) | ModernBERT | 679M | 548M | | |
| | [iamtatsuki05/Llama-JP-0.5B-PT-stage1](https://huggingface.co/iamtatsuki05/Llama-JP-0.5B-PT-stage1) | Llama | 661M | 530M | | |
| ## Licence | |
| このモデルは [MIT](https://licenses.opensource.jp/MIT/MIT.html) でライセンスされています。 | |
| ## How to Cite | |
| ```tex | |
| @article{MIREI | |
| title={同一条件下における Encoder/Decoder アーキテクチャによる文埋め込みの性能分析}, | |
| author={岡田 龍樹 and 杉本 徹}, | |
| journal={言語処理学会第 32 回年次大会 (NLP2026)}, | |
| year={2026} | |
| } | |
| ``` | |