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
Card: point MTEB(por) link to mteb-pt leaderboard
Browse files
README.md
CHANGED
|
@@ -73,7 +73,7 @@ tax, financial, medical, academic and general domains.
|
|
| 73 |
|
| 74 |
## 🥇 Quality — MTEB(por)
|
| 75 |
|
| 76 |
-
Evaluated on **[MTEB(por)](https://huggingface.co/spaces/mteb/leaderboard)** (22 native Brazilian-Portuguese tasks:
|
| 77 |
retrieval, reranking, STS, classification, clustering, pair-classification). Score = mean over the 22 tasks.
|
| 78 |
|
| 79 |
| Model | Params | MTEB(por) |
|
|
@@ -212,7 +212,7 @@ Both operations yield ordinary weights, so the published model is a single stand
|
|
| 212 |
- Base: [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) · Trimmed base: [tardellirs/embeddinggemma-pt-br](https://huggingface.co/tardellirs/embeddinggemma-pt-br)
|
| 213 |
- Trimming code: [github.com/tardellirs/embedding-vocab-trimmer](https://github.com/tardellirs/embedding-vocab-trimmer)
|
| 214 |
- Distillation teachers: [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) · [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B)
|
| 215 |
-
- Benchmark: [MTEB(por)](https://huggingface.co/spaces/mteb/leaderboard) · CPU benchmark hardware: [Verda](https://verda.com/?utm_content=mteb-pt)
|
| 216 |
|
| 217 |
---
|
| 218 |
|
|
|
|
| 73 |
|
| 74 |
## 🥇 Quality — MTEB(por)
|
| 75 |
|
| 76 |
+
Evaluated on **[MTEB(por)](https://huggingface.co/spaces/mteb-pt/leaderboard)** (22 native Brazilian-Portuguese tasks:
|
| 77 |
retrieval, reranking, STS, classification, clustering, pair-classification). Score = mean over the 22 tasks.
|
| 78 |
|
| 79 |
| Model | Params | MTEB(por) |
|
|
|
|
| 212 |
- Base: [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) · Trimmed base: [tardellirs/embeddinggemma-pt-br](https://huggingface.co/tardellirs/embeddinggemma-pt-br)
|
| 213 |
- Trimming code: [github.com/tardellirs/embedding-vocab-trimmer](https://github.com/tardellirs/embedding-vocab-trimmer)
|
| 214 |
- Distillation teachers: [Qwen/Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) · [Qwen/Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B)
|
| 215 |
+
- Benchmark: [MTEB(por)](https://huggingface.co/spaces/mteb-pt/leaderboard) · CPU benchmark hardware: [Verda](https://verda.com/?utm_content=mteb-pt)
|
| 216 |
|
| 217 |
---
|
| 218 |
|