Update README.md
Browse files
README.md
CHANGED
@@ -129,7 +129,7 @@ model-index:
|
|
129 |
value: 0.7694903427297795
|
130 |
name: Cosine Recall@10
|
131 |
- type: cosine_ndcg@10
|
132 |
-
value: 0.
|
133 |
name: Cosine Ndcg@10
|
134 |
- type: cosine_mrr@10
|
135 |
value: 0.7262426410313736
|
@@ -187,6 +187,10 @@ base_model:
|
|
187 |
- BAAI/bge-m3
|
188 |
---
|
189 |
|
|
|
|
|
|
|
|
|
190 |
# SentenceTransformer
|
191 |
|
192 |
This is a [sentence-transformers](https://www.SBERT.net) model trained on the train_set dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
@@ -401,7 +405,7 @@ This is a benchmark of Korean embedding models.
|
|
401 |
| cosine_recall@3 | 0.5902 |
|
402 |
| cosine_recall@5 | 0.6794 |
|
403 |
| cosine_recall@10 | 0.7695 |
|
404 |
-
| **cosine_ndcg@10** | **0.
|
405 |
| cosine_mrr@10 | 0.7262 |
|
406 |
| cosine_map@100 | 0.6074 |
|
407 |
| dot_accuracy@1 | 0.6103 |
|
|
|
129 |
value: 0.7694903427297795
|
130 |
name: Cosine Recall@10
|
131 |
- type: cosine_ndcg@10
|
132 |
+
value: 0.6833112035481234
|
133 |
name: Cosine Ndcg@10
|
134 |
- type: cosine_mrr@10
|
135 |
value: 0.7262426410313736
|
|
|
187 |
- BAAI/bge-m3
|
188 |
---
|
189 |
|
190 |
+
|
191 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/642b0c2fecec03b4464a1d9b/IxcqY5qbGNuGpqDciIcOI.webp" width="600">
|
192 |
+
|
193 |
+
|
194 |
# SentenceTransformer
|
195 |
|
196 |
This is a [sentence-transformers](https://www.SBERT.net) model trained on the train_set dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
|
|
405 |
| cosine_recall@3 | 0.5902 |
|
406 |
| cosine_recall@5 | 0.6794 |
|
407 |
| cosine_recall@10 | 0.7695 |
|
408 |
+
| **cosine_ndcg@10** | **0.6833** |
|
409 |
| cosine_mrr@10 | 0.7262 |
|
410 |
| cosine_map@100 | 0.6074 |
|
411 |
| dot_accuracy@1 | 0.6103 |
|