Daily download history, rankings and derivative families for every model on the Hub.
Tardelli Stekel
tardellirs
P(doom) <0.001%
·
AI & ML interests
None yet
Recent Activity
updated a Space about 7 hours ago
tardellirs/model-pulse updated a Space about 7 hours ago
tardellirs/paper-pulse updated a dataset about 7 hours ago
tardellirs/paper-pulse-dataOrganizations
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 • 2.47k • 1 -
tardellirs/embeddinggemma-pt-br-128k
Sentence Similarity • 0.2B • Updated • 78 • 1 -
tardellirs/embeddinggemma-pt-br-48k
Sentence Similarity • 0.1B • Updated • 71 • 1 -
tardellirs/embeddinggemma-pt-br-32k
Sentence Similarity • 0.1B • Updated • 62 • 2
Daily download history, rankings and derivative families for every model on the Hub.
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).
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 • 2.47k • 1 -
tardellirs/embeddinggemma-pt-br-128k
Sentence Similarity • 0.2B • Updated • 78 • 1 -
tardellirs/embeddinggemma-pt-br-48k
Sentence Similarity • 0.1B • Updated • 71 • 1 -
tardellirs/embeddinggemma-pt-br-32k
Sentence Similarity • 0.1B • Updated • 62 • 2