Model reference · open weights
med-ruri-from-med is an open-weight embedding model from genshiai-daichi. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | genshiai-daichi |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 315M |
| Context | 8k tokens |
| Runs with | sentence-transformers |
| Based on | genshiai-daichi/med-ruri-v3-310m |
| Released | 2026-06-14 |
| Popularity | 504 downloads / month |
| Licence | Open weights |
About
日本語医療ドメインの文埋め込みモデル (ruri-v3 / ModernBERT-Ja ベース)。学習進行中の自動アップロードです。
継続学習: 既に医療 fine-tune 済みの genshiai-daichi/med-ruri-v3-310m(v1) の上に v2 レシピで追加学習
9238 / in-domain nDCG@10: 0.5348step-9238 の revision ブランチで固定取得可。main は最新/最終。※ 同一ガイドライン分布の held-out クエリ + 3万 distractor での検索性能。
汎化/temporal の優劣はこの指標では測れない (別途 ood_affinity で評価)。
| step | nDCG@10 |
|---|---|
| 500 | 0.4195 |
| 1000 | 0.4300 |
| 1500 | 0.4422 |
| 2000 | 0.4640 |
| 2500 | 0.4623 |
| 3000 | 0.4700 |
| 3500 | 0.4775 |
| 4000 | 0.4920 |
| 4500 | 0.4916 |
| 5000 | 0.5025 |
| 5500 | 0.4996 |
| 6000 | 0.5008 |
| 6500 | 0.5120 |
| 7000 | 0.5179 |
| 7500 | 0.5243 |
| 8000 | 0.5287 |
| 8500 | 0.5305 |
| 9000 | 0.5343 |
| 9238 | 0.5348 |
metrics_progress.jsonstep-N ブランチの runs/ に同梱 (tensorboard --logdir runs で loss/nDCG を可視化可)。検索クエリ: / document=検索文書: (付けないと精度が大きく落ちる)from sentence_transformers import SentenceTransformer
m = SentenceTransformer("genshiai-daichi/med-ruri-v3-310m-v2-from-med", revision="step-9238") # main で最新も可
q = m.encode(["検索クエリ: 心不全の標準治療は"], normalize_embeddings=True)
d = m.encode(["検索文書: 【…】 …本文…"], normalize_embeddings=True)
metrics_progress.json を参照。From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys med-ruri-from-med for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (med-ruri-from-med 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":"med-ruri-from-med","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.