mrm8488
/

multilingual-e5-large-ft-sts-spanish-matryoshka-768-64-5e

Sentence Similarity

sentence-transformers

feature-extraction

dataset_size:1K<n<10K

loss:MatryoshkaLoss

loss:CoSENTLoss

text-embeddings-inference

Inference Endpoints

Model card Files Files and versions Community

mrm8488 commited on 28 days ago

Commit

6802647

•

1 Parent(s): a98256c

Update README.md

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -435,7 +435,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [i
 - **Output Dimensionality:** 1024 tokens
 - **Similarity Function:** Cosine Similarity
 - **Training Dataset:**
-    - clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
@@ -701,9 +701,9 @@ You can finetune this model on your own dataset.
 ### Training Dataset
-#### clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
-* Dataset: clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
 * Size: 2,697 training samples
 * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
 * Approximate statistics based on the first 1000 samples:
@@ -741,9 +741,9 @@ You can finetune this model on your own dataset.
 ### Evaluation Dataset
-#### clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
-* Dataset: clibrain/stsb_multi_es_aug_gpt3.5-turbo_2
 * Size: 697 evaluation samples
 * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
 * Approximate statistics based on the first 1000 samples:

 - **Output Dimensionality:** 1024 tokens
 - **Similarity Function:** Cosine Similarity
 - **Training Dataset:**
+    - stsb_multi_es_aug
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
 ### Training Dataset
+#### stsb_multi_es_aug
+* Dataset: stsb_multi_es_aug
 * Size: 2,697 training samples
 * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
 * Approximate statistics based on the first 1000 samples:
 ### Evaluation Dataset
+#### stsb_multi_es_aug
+* Dataset: stsb_multi_es_aug
 * Size: 697 evaluation samples
 * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
 * Approximate statistics based on the first 1000 samples: