sarashina-embedding-v1-1b
"Sarashina-Embedding-v1-1B" is a Japanese text embedding model, based on the 1.2B-parameter Japanese LLM "Sarashina2.1-1B". We trained this model with multi-stage contrastive learning. We achieved the state-of-the-art average score across 16 datasets in JMTEB (Japanese Massive Text Embedding Benchmark).
Params
1.2 B
Context
8,192
Downloads 30d
413 K
Likes
38
Download history
daily snapshots · 15 days462 K408 K
Sep 7Sep 12Sep 17Sep 21
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 4.9 GB | 6.1 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Specifications
- Architecture
- LlamaModel
- Parameters
- 1.2 B
- Tensor type
- F32
- Context length
- 8,192
- Vocabulary
- 102,400
- Layers / heads
- 24 / 16
- First seen on the Hub
- 2024-11-22
- Training datasets
- hpprc/emb, cl-nagoya/auto-wiki-qa, cl-nagoya/ruri-dataset-ft, hpprc/mqa-ja, izumi-lab/llm-japanese-dataset, sentence-transformers/NQ-retrieval, sbintuitions/JSQuAD, SkelterLabsInc/JaQuAD, wikimedia/wikipedia, cl-nagoya/nu-mnli, castorini/mr-tydi
- Added to our catalog
- 2026-09-07
Compare with any sentence-similarity model