Model reference · open weights
ritrieve_zh is an open-weight embedding model from richinfoai. 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 | richinfoai |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 326M |
| Context | 512 tokens |
| Runs with | sentence-transformers |
| Released | 2025-03-25 |
| Popularity | 942 downloads / month |
| Licence | Open weights |
About
This model was trained by richinfoai. Followed Stella and Jasper models, we do distillation training from lier007/xiaobu-embedding-v2, dunzhang/stella-large-zh-v3-1792d and BAAI/bge-multilingual-gemma2. Thanks to their outstanding performance, our model has achieved excellent results on MTEB(cmn, v1).
We believe this model once again demonstrates the effectiveness of distillation learning. In the future, we will train more bilingual vector models based on various excellent vector training methods.
We use BAAI/Infinity-Instruct and opencsg/chinese-fineweb-edu as training data to do a distillation from the above three models. In this stage, we only use cosine-loss.
The objective of stage2 is reducing dimensions.
We use the same training data as the stage1 with similarity loss. After stage2, the dimensions of our model is 1792.
This model does not need instructions and you can use it in SentenceTransformer:
import os
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
from sentence_transformers import SentenceTransformer
text_encoder = SentenceTransformer("richinfoai/ritrieve_zh_v1")
texts = [
"什么是人工智能",
"介绍一下主流的LLM",
"人工智能（AI）是模拟人类智能的计算机系统，能够执行学习、推理和决策等任务。它通过算法和大数据实现自动化，广泛应用于各行各业。"
]
vectors = text_encoder.encode(texts, normalize_embeddings=True)
print(vectors @ vectors.T)
# [[0.9999999 0.67707014 0.91421044]
# [0.67707014 0.9999998 0.6353945 ]
# [0.91421044 0.6353945 1.0000001 ]]
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys ritrieve-zh for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ritrieve-zh 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":"ritrieve-zh","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.