The MTEB(por) benchmark for Brazilian Portuguese (leaderboard + task datasets) and the Colibri embedding model that tops it among small models.
Tardelli Stekel
tardellirs
AI & ML interests
None yet
Recent Activity
updated a Space 1 day ago
MTEB-BR/leaderboard updated a model 1 day ago
MTEB-BR/baseline-random-encoder updated a dataset 2 days ago
MTEB-BR/juristcu-rerankingOrganizations
Contamination-clean ~110M Brazilian-Portuguese embeddings (BERTimbau). #1 in the ~100M class on MTEB(por).
-
tardellirs/brazembed-pt-br
Sentence Similarity • 0.1B • Updated • 181 • 1 -
tardellirs/brazembed-pt-br-clfclu
Sentence Similarity • 0.1B • Updated • 122 -
tardellirs/brazembed-pt-br-pairclf
Sentence Similarity • 0.1B • Updated • 118 -
tardellirs/brazembed-pt-br-sts
Sentence Similarity • 0.1B • Updated • 105
Compact pt-br text-embedding model (~157M) that beats far larger models on MTEB(por): vocabulary trim -> Qwen3-4B distillation -> model soup.
Portuguese EmbeddingGemma-300M, vocab-trimmed 16k–128k. Training-free; 64k ≈ full quality at half the params.
-
tardellirs/embeddinggemma-pt-br
Sentence Similarity • 0.2B • Updated • 852 • 1 -
tardellirs/embeddinggemma-pt-br-128k
Sentence Similarity • 0.2B • Updated • 116 • 1 -
tardellirs/embeddinggemma-pt-br-48k
Sentence Similarity • 0.1B • Updated • 118 • 1 -
tardellirs/embeddinggemma-pt-br-32k
Sentence Similarity • 0.1B • Updated • 130 • 2
The MTEB(por) benchmark for Brazilian Portuguese (leaderboard + task datasets) and the Colibri embedding model that tops it among small models.
Compact pt-br text-embedding model (~157M) that beats far larger models on MTEB(por): vocabulary trim -> Qwen3-4B distillation -> model soup.
Contamination-clean ~110M Brazilian-Portuguese embeddings (BERTimbau). #1 in the ~100M class on MTEB(por).
-
tardellirs/brazembed-pt-br
Sentence Similarity • 0.1B • Updated • 181 • 1 -
tardellirs/brazembed-pt-br-clfclu
Sentence Similarity • 0.1B • Updated • 122 -
tardellirs/brazembed-pt-br-pairclf
Sentence Similarity • 0.1B • Updated • 118 -
tardellirs/brazembed-pt-br-sts
Sentence Similarity • 0.1B • Updated • 105
Portuguese EmbeddingGemma-300M, vocab-trimmed 16k–128k. Training-free; 64k ≈ full quality at half the params.
-
tardellirs/embeddinggemma-pt-br
Sentence Similarity • 0.2B • Updated • 852 • 1 -
tardellirs/embeddinggemma-pt-br-128k
Sentence Similarity • 0.2B • Updated • 116 • 1 -
tardellirs/embeddinggemma-pt-br-48k
Sentence Similarity • 0.1B • Updated • 118 • 1 -
tardellirs/embeddinggemma-pt-br-32k
Sentence Similarity • 0.1B • Updated • 130 • 2