iamtatsuki05/Sentence-Sarashina-Bi-0.5B
079
Sentence-Sarashina-Bi-0.5B
English / Japanese
Overview
Sentence-Sarashina-Bi-0.5B fine-tunes iamtatsuki05/Sentence-Sarashina-Bi-0.5B-PT with supervised examples from cl-nagoya/ruri-v3-dataset-ft, resulting in 1,280-dimensional Japanese embeddings.
- [Hugging Face Collection](https://huggingface.co/collections/iamtatsuki05/mirei)
- [GitHub](https://github.com/iamtatsuki05/MIREI)
Usage
Requirements
sentence-transformers>=4.1.0
transformers>=4.51.0
accelerate>=1.6.0
sentencepiece>=0.2.0
flash-attn>=2.7.3Sample Code
import torch
from sentence_transformers import SentenceTransformer
model_name = "iamtatsuki05/Sentence-Sarashina-Bi-0.5B"
model_kwargs = {
"torch_dtype": torch.bfloat16,
"attn_implementation": "flash_attention_2",
}
model = SentenceTransformer(model_name, model_kwargs=model_kwargs)
queries = ["ハチワレはどのようなキャラクターですか？"]
docs = [
"ハチワレは、『ちいかわ』に登場する猫風のキャラクターで、明るく社交的、前向きな性格が特徴。ちいかわたちと共に日常を楽しみつつ、討伐などの冒険にも積極的に挑む存在です。",
"うさぎは、天真爛漫でマイペースな性格が特徴のキャラクターで、突飛な行動力と鋭い直感でちいかわたちを引っ張る存在。自由気ままながらも仲間思いな一面を併せ持ちます。",
]
q_emb = model.encode(queries, normalize_embeddings=True)
d_emb = model.encode(docs, normalize_embeddings=True)
scores = model.similarity(q_emb, d_emb)
print(scores)Model Details
- Base model: iamtatsuki05/Sentence-Sarashina-Bi-0.5B-PT
- Architecture: Llama
- Maximum sequence length: 8,192 tokens
- Embedding dimension: 1280 (mean pooling)
- Tokenizer: SentencePiece / vocabulary size 102,400
- Positional encoding: RoPE
- Supported languages: Japanese
- Similarity metric: cosine
Model Series
The encoders below inherit from weakly supervised models and receive supervised refinement on cl-nagoya/ruri-v3-dataset-ft.
Licence
This model is distributed under the MIT License.
How to Cite
@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}
}