rasyosef
/

roberta-amharic-text-embedding-base

Sentence Similarity

sentence-transformers

feature-extraction

Generated from Trainer

dataset_size:40237

loss:MatryoshkaLoss

loss:MultipleNegativesRankingLoss

text-embeddings-inference

Model card Files Files and versions Community

rasyosef commited on May 25

Commit

cae2812

·

verified ·

1 Parent(s): bad738b

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -459,7 +459,7 @@ model-index:
 # RoBERTa Amharic Text Embedding Base
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [rasyosef/roberta-base-amharic](https://huggingface.co/rasyosef/roberta-base-amharic) on the [amharic-news-retrieval-dataset](https://huggingface.co/datasets/rasyosef/amharic-news-retrieval-dataset) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 ## Model Details
@@ -470,7 +470,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [r
 - **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 - **Training Dataset:**
-    - [amharic-news-retrieval-dataset](https://huggingface.co/datasets/rasyosef/amharic-news-retrieval-dataset)
 - **Language:** am
 - **License:** apache-2.0
@@ -624,7 +624,7 @@ You can finetune this model on your own dataset.
 #### amharic-news-retrieval-dataset
-* Dataset: [amharic-news-retrieval-dataset](https://huggingface.co/datasets/rasyosef/amharic-news-retrieval-dataset) at [3ef7092](https://huggingface.co/datasets/rasyosef/amharic-news-retrieval-dataset/tree/3ef7092c24f5494b79b09e0264b73528044c1c03)
 * Size: 40,237 training samples
 * Columns: <code>anchor</code> and <code>positive</code>
 * Approximate statistics based on the first 1000 samples:

 # RoBERTa Amharic Text Embedding Base
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [rasyosef/roberta-base-amharic](https://huggingface.co/rasyosef/roberta-base-amharic) on the [amharic-passage-retrieval-dataset](https://huggingface.co/datasets/rasyosef/amharic-passage-retrieval-dataset) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 ## Model Details
 - **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 - **Training Dataset:**
+    - [amharic-passage-retrieval-dataset](https://huggingface.co/datasets/rasyosef/amharic-passage-retrieval-dataset)
 - **Language:** am
 - **License:** apache-2.0
 #### amharic-news-retrieval-dataset
+* Dataset: [amharic-passage-retrieval-dataset](https://huggingface.co/datasets/rasyosef/amharic-passage-retrieval-dataset) at [3ef7092](https://huggingface.co/datasets/rasyosef/amharic-passage-retrieval-dataset/tree/3ef7092c24f5494b79b09e0264b73528044c1c03)
 * Size: 40,237 training samples
 * Columns: <code>anchor</code> and <code>positive</code>
 * Approximate statistics based on the first 1000 samples: