alphaedge-ai / bge-m3-mkd-16384

huggingface.co
Total runs: 92
24-hour runs: 0
7-day runs: 8
30-day runs: 0
Model's Last Updated: May 20 2026
sentence-similarity

Introduction of bge-m3-mkd-16384

Model Details of bge-m3-mkd-16384

bge-m3-mkd-16384

This model is a 42.14% smaller version of BAAI/bge-m3 optimized for Macedonian language via vocabulary size reduction using the trimming method.
This trimmed model should perform similarly to the original model with only 16,384 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in the selected languages were removed from the vocabulary.

Model Statistics
Metric Original Trimmed Reduction
Vocabulary size 250,002 tokens 16,384 tokens 93.45%
Model size 567,754,752 params 328,529,920 params 42.14%

image

Mining Dataset Statistics
Usage
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("alphaedge-ai/bge-m3-mkd-16384")
# Run inference with queries and documents
query = "My query in Macedonian"
documents = [
    "Chunk in Macedonian",
    "Chunk in Macedonian",
    "Chunk in Macedonian",
]
query_embeddings = model.encode_query(query)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# Compute similarities to determine a ranking
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
Citations
BGE-M3
@misc{bge-m3,
      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
      year={2024},
      eprint={2402.03216},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
Trimming blog post
@misc{hf_blogpost_trimming,
      title={Introduction to Trimming}, 
      author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
      year={2026},
      url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, 
}

Runs of alphaedge-ai bge-m3-mkd-16384 on huggingface.co

92
Total runs
0
24-hour runs
-14
3-day runs
8
7-day runs
0
30-day runs

More Information About bge-m3-mkd-16384 huggingface.co Model

More bge-m3-mkd-16384 license Visit here:

https://choosealicense.com/licenses/mit

bge-m3-mkd-16384 huggingface.co

bge-m3-mkd-16384 huggingface.co is an AI model on huggingface.co that provides bge-m3-mkd-16384's model effect (), which can be used instantly with this alphaedge-ai bge-m3-mkd-16384 model. huggingface.co supports a free trial of the bge-m3-mkd-16384 model, and also provides paid use of the bge-m3-mkd-16384. Support call bge-m3-mkd-16384 model through api, including Node.js, Python, http.

alphaedge-ai bge-m3-mkd-16384 online free

bge-m3-mkd-16384 huggingface.co is an online trial and call api platform, which integrates bge-m3-mkd-16384's modeling effects, including api services, and provides a free online trial of bge-m3-mkd-16384, you can try bge-m3-mkd-16384 online for free by clicking the link below.

alphaedge-ai bge-m3-mkd-16384 online free url in huggingface.co:

https://huggingface.co/alphaedge-ai/bge-m3-mkd-16384

bge-m3-mkd-16384 install

bge-m3-mkd-16384 is an open source model from GitHub that offers a free installation service, and any user can find bge-m3-mkd-16384 on GitHub to install. At the same time, huggingface.co provides the effect of bge-m3-mkd-16384 install, users can directly use bge-m3-mkd-16384 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

bge-m3-mkd-16384 install url in huggingface.co:

https://huggingface.co/alphaedge-ai/bge-m3-mkd-16384

Url of bge-m3-mkd-16384

bge-m3-mkd-16384 huggingface.co Url

Provider of bge-m3-mkd-16384 huggingface.co

alphaedge-ai
ORGANIZATIONS

Other API from alphaedge-ai