---
license: gemma
language:
- pt
library_name: sentence-transformers
pipeline_tag: sentence-similarity
base_model: google/embeddinggemma-300m
tags:
- sentence-transformers
- embeddings
- portuguese
- vocabulary-trimming
- mteb
---

# embeddinggemma-pt-br-48k

A **Portuguese-only** text-embedding model, **vocabulary-trimmed** from
[`google/embeddinggemma-300m`](https://huggingface.co/google/embeddinggemma-300m) to a **48k** token
vocabulary (**~144M params**, MTEB(por) `mean_16` **0.7098** = **97.8% of the full model** at
47% of its size). No training — only the token embedding matrix was sliced; the transformer
encoder and pooling/Dense heads are identical to the base model. Produced with
🛠️ **[embedding-vocab-trimmer](https://github.com/tardellirs/embedding-vocab-trimmer)**.

Part of the **embeddinggemma-pt-br** family — [**64k**](https://huggingface.co/tardellirs/embeddinggemma-pt-br) is the recommended sweet spot:

| model | params | `mean_16` | % of full |
|---|---:|:---:|:---:|
| google/embeddinggemma-300m | ~308M | 0.7257 | 100% |
| [embeddinggemma-pt-br-128k](https://huggingface.co/tardellirs/embeddinggemma-pt-br-128k) | ~207M | 0.7192 | 99.1% |
| [embeddinggemma-pt-br](https://huggingface.co/tardellirs/embeddinggemma-pt-br) | ~157M | 0.7172 | 98.8% |
| [embeddinggemma-pt-br-48k](https://huggingface.co/tardellirs/embeddinggemma-pt-br-48k) ⭐ | ~144M | 0.7098 | 97.8% |
| [embeddinggemma-pt-br-32k](https://huggingface.co/tardellirs/embeddinggemma-pt-br-32k) | ~131M | 0.6881 | 94.8% |
| [embeddinggemma-pt-br-24k](https://huggingface.co/tardellirs/embeddinggemma-pt-br-24k) | ~125M | 0.6895 | 95.0% |
| [embeddinggemma-pt-br-16k](https://huggingface.co/tardellirs/embeddinggemma-pt-br-16k) | ~119M | 0.6520 | 89.8% |

## Usage
```python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("tardellirs/embeddinggemma-pt-br-48k")
emb = model.encode(["O Brasil é um país tropical da América do Sul."], normalize_embeddings=True)
```
Uses EmbeddingGemma's task prompts (prepend `task: search result | query: ` / `title: none | text: ` for retrieval).

## Scope
A **compression** of Google's EmbeddingGemma to Portuguese (deployment/efficiency artifact; data provenance is the base model's). Vocabulary trimming compresses, it does not enhance. Derived under the [Gemma license](https://ai.google.dev/gemma/terms).

Benchmark: [MTEB(por)](https://huggingface.co/MTEB-BR) · [leaderboard](https://huggingface.co/spaces/MTEB-BR/leaderboard).