Sentence Similarity
sentence-transformers
Safetensors
Portuguese
gemma3_text
embeddings
portuguese
vocabulary-trimming
mteb
text-embeddings-inference
Instructions to use tardellirs/embeddinggemma-pt-br-48k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use tardellirs/embeddinggemma-pt-br-48k with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("tardellirs/embeddinggemma-pt-br-48k") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Point benchmark links to MTEB-BR org (renamed from mteb-pt)
Browse files
README.md
CHANGED
|
@@ -45,4 +45,4 @@ Uses EmbeddingGemma's task prompts (prepend `task: search result | query: ` / `t
|
|
| 45 |
## Scope
|
| 46 |
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).
|
| 47 |
|
| 48 |
-
Benchmark: [MTEB(por)](https://huggingface.co/
|
|
|
|
| 45 |
## Scope
|
| 46 |
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).
|
| 47 |
|
| 48 |
+
Benchmark: [MTEB(por)](https://huggingface.co/MTEB-BR) 路 [leaderboard](https://huggingface.co/spaces/MTEB-BR/leaderboard).
|