Sentence Similarity
sentence-transformers
Safetensors
Portuguese
gemma3_text
feature-extraction
embeddings
text-embeddings
text-embeddings-inference
retrieval
information-retrieval
semantic-search
rag
reranking
clustering
sts
portuguese
pt-br
brazilian-portuguese
mteb
vocabulary-trimming
knowledge-distillation
model-soup
Instructions to use tardellirs/colibri-embed-ptbr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use tardellirs/colibri-embed-ptbr with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("tardellirs/colibri-embed-ptbr") 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] - Inference
- Notebooks
- Google Colab
- Kaggle
Colibri — multi-teacher (Qwen3-4B + 8B) distilled PT-BR embeddings, MTEB(por) 0.6501
d6e7cef verified Download sentence_bert_config.json from tardellirs/colibri-embed-ptbr: direct link, hf CLI and curl.
- Browser
- Download file 241 Bytes
-
https://huggingface.co/tardellirs/colibri-embed-ptbr/resolve/main/sentence_bert_config.json
- Command line
-
hf download hf://tardellirs/colibri-embed-ptbr/sentence_bert_config.json
-
curl -L -o sentence_bert_config.json https://huggingface.co/tardellirs/colibri-embed-ptbr/resolve/main/sentence_bert_config.json
241 Bytes
| { | |
| "transformer_task": "feature-extraction", | |
| "modality_config": { | |
| "text": { | |
| "method": "forward", | |
| "method_output_name": "last_hidden_state" | |
| } | |
| }, | |
| "module_output_name": "token_embeddings" | |
| } |