README.md

---
pipeline_tag: sentence-similarity
language: nep
license: mit
tags:
  - trimmed
library_name: sentence-transformers
base_model: BAAI/bge-m3
base_model_relation: quantized
datasets:
  - lbourdois/fineweb-2-trimming
---

# bge-m3-nep-16384
This model is a **42.14% smaller** version of [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) optimized for Nepali language via vocabulary size reduction using the [trimming](https://huggingface.co/blog/lbourdois/introduction-to-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](https://raw.githubusercontent.com/lbourdois/blog/refs/heads/master/assets/images/Trimming/bge-m3-16384.png)

## Mining Dataset Statistics
- **Number of texts used for mining**: 29,721 texts  
- **Dataset**: [lbourdois/fineweb-2-trimming](https://huggingface.co/datasets/lbourdois/fineweb-2-trimming)

## Usage

```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("alphaedge-ai/bge-m3-nep-16384")
# Run inference with queries and documents
query = "My query in Nepali"
documents = [
    "Chunk in Nepali",
    "Chunk in Nepali",
    "Chunk in Nepali",
]
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}, 
}
```