Model reference · open weights
japanese-reranker-cross-encoder-xsmall is an open-weight embedding model from hotchpotch, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
hotchpotch/japanese-reranker-cross-encoder-xsmall-v1 日本語で学習させた Reranker (CrossEncoder) シリーズです。 Reranker についてや、技術レポート・評価等は以下を参考ください。 - 日本語最高性能のRerankerをリリース / そもそも Reranker とは? - 日本語 Reranker 作成のテクニカルレポート 使い方 SentenceTransformers HuggingFace transformers 評価結果 ライセンス MIT License
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | hotchpotch |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 107M |
| Context | 514 tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Released | 2024-03-28 |
| Popularity | 62k downloads / month |
| Likes | 7 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| japanese-reranker-cross-encoder-xsmall-v1 | 107M | BF16 | ~0.2 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys japanese-reranker-cross-encoder-xsmall for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (japanese-reranker-cross-encoder-xsmall below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"japanese-reranker-cross-encoder-xsmall","input":"text to embed"}'
Details
Languages
Trained / evaluated on
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore