Views
No views yet
| Model Name | Model Size | C-MTEB(35) | MTEB(56) | avg |
|---|---|---|---|---|
| multilingual-e5-large | 560M | 58.81 | 61.5 | 60.16 |
| bge-m3 (dense) | 560M | 60.80 | 59.84 | 60.32 |
| gte-multilingual-base (dense) | 305M | 62.72 | 61.40 | 62.06 |
| KaLM-embedding-multilingual-mini-v1 | 494M | 62.31 | 61.87 | 62.09 |
| KaLM-embedding-multilingual-mini-instruct-v1 | 494M | 63.57 | 64.74 | 64.16 |
| KaLM-embedding-multilingual-mini-instruct-v1.5 | 494M | 64.13 | 64.94 | 64.53 |
transformers>=4.37.0, or you might encounter the following error:KeyError: 'qwen2'pip install -U sentence-transformers1from sentence_transformers import SentenceTransformer
2
3
4sentences = ["This is an example sentence", "Each sentence is converted"]
5
6model = SentenceTransformer('{MODEL_NAME_OR_PATH}') # Do NOT set trust_remote_code
7model.max_seq_length = 512
8
9embeddings = model.encode(
10 sentences,
11 normalize_embeddings=True,
12 batch_size=256,
13 show_progress_bar=True
14 )
15print(embeddings)1from sentence_transformers import SentenceTransformer
2
3
4sentences = ["This is an example sentence", "Each sentence is converted"]
5
6model = SentenceTransformer('{MODEL_NAME_OR_PATH}') # Do NOT set trust_remote_code
7model.max_seq_length = 512
8
9prompt = "Instruct: Classifying the category of french news. \n Query: "
10embeddings = model.encode(
11 sentences,
12 prompt=prompt,
13 normalize_embeddings=True,
14 batch_size=256,
15 show_progress_bar=True
16 )
17print(embeddings)@article{hu2025kalm,
title={KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model},
author={Hu, Xinshuo and Shan, Zifei and Zhao, Xinping and Sun, Zetian and Liu, Zhenyu and Li, Dongfang and Ye, Shaolin and Wei, Xinyuan and Chen, Qian and Hu, Baotian and others},
journal={arXiv preprint arXiv:2501.01028},
year={2025}
}