---
base_model: rasyosef/roberta-medium-amharic
datasets:
- rasyosef/Amharic-Passage-Retrieval-Dataset-V2
language:
- am
library_name: sentence-transformers
license: mit
metrics:
- cosine_recall@5
- cosine_recall@10
- cosine_ndcg@10
- cosine_mrr@10
pipeline_tag: text-retrieval
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- generated_from_trainer
- dataset_size:122938
- loss:MatryoshkaLoss
- loss:MultipleNegativesRankingLoss
widget:
- source_sentence: በኢትዮጵያ ለመጀመሪያ ጊዜ ወታደራዊ ስልጠና የወሰዱ ዕጩ ዲፕሎማቶች ተመረቁ
  sentences:
  - የውጭ ጉዳይ ሚኒስቴር ከሜጀር ጄነራል ሀየሎም አርአያ ወታደራዊ አካዳሚ ጋር በመተባበር በኢትዮጵያ ለመጀመሪያ ጊዜ ወታደራዊ
    ስልጠና የወሰዱ ዲፕሎማቶችን  አስመረቀ፡፡በወታደራዊ አካዳሚው ትላንት በተካሄደ የምርቃት ሥነ- ስርዓት ስልጠናውን ላገኙ 89
    ዕጩ ድፕሎማቶች የምስክር ወረቀት ተበረክቷል።
  - አዲስ አበባ፣ የካቲት 19፣ 2012 (ኤፍ.ቢ.ሲ) የኢፌዴሪ አየር ኃይል ለከፍተኛ መኮንኖች የማዕረግ እድገት ሰጥቷል።አየር
    ኃይሉ በዛሬው እለት በቢሾፍቱ በሚገኘው የኢፌዴሪ አየር ኃይል ጠቅላይ መምሪያ ባካሄደው ስነ ስርዓት ላይ የኢፌዴሪ ጦር ኃይሎች
    ምክተል ኤታማዦር ሹም ጄኔራል ብርሃኑ ጁላ እና የኢፌዴሪ አየር ኃይል ዋና አዛዥ ሜጀር ጄኔራል ይልማ መርዳሳን ጨምሮ ከፍተኛ
    አመራሮች ተገኝተዋል።በስነ ስርዓቱ ላይ 106 ለሚሆኑ መኮንኖች በአየር ኃይል ዋና አዛዥ ሜጀር ጄኔራል ይልማ መርዳሳ የተለያዩ
    የማዕረግ እድገቶችን ሰጥተዋል።
- source_sentence: ኢትዮጵያ ኢንተርኔትን በመዝጋቷ ከ130 ሚሊዮን ዶላር በላይ አጣች
  sentences:
  - የአሜሪካ ድምፅ ባለፉት ሰባ አምስት ዓመታት ውስጥ በዓለም ዙሪያ ያሉ የተለያዩ አድማጮችና ተመልካቾች ከሌሎች ምንጮች ሊያገኟቸው
    የማይችሏቸውን መረጃዎች ለዓለም ሲያደርስ መቆየቱን ዋና ዳይሬክተሯ አማንዳ ቤኔት ገልፀዋል።
  - የተቋሙ ጥናት የኢንተርኔን መዘጋት በሃገራት ምጣኔ ሐብት ላይ ያደረሰውን ጉዳት በተለያዩ መለኪያዎች የገመተ ሲሆን፤ በዚህም
    መሰረት ኢትዮጵያ ለ36 ቀናት ያህል ኢንተርኔትን በዘጋችበት እንዲሁም ለሰባት ቀናት ያህል በነበረው የማኅበራዊ ሚዲያ መናወጥ\
    ወቅት በጥቅሉ ከ130 ሚሊዮን ዶላር በላይ አጥታለች ይላል።
model-index:
- name: Embedding Amharic Medium
  results:
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 512
      type: dim_512
    metrics:
    - type: cosine_recall@5
      value: 0.8429994141769186
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.8882542472173404
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.7794100902238014
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.7444322979142834
      name: Cosine Mrr@10
  - task:
      type: information-retrieval
      name: Information Retrieval
    dataset:
      name: dim 256
      type: dim_256
    metrics:
    - type: cosine_recall@5
      value: 0.8409490333919156
      name: Cosine Recall@5
    - type: cosine_recall@10
      value: 0.883128295254833
      name: Cosine Recall@10
    - type: cosine_ndcg@10
      value: 0.7735557850747518
      name: Cosine Ndcg@10
    - type: cosine_mrr@10
      value: 0.7382452971424844
      name: Cosine Mrr@10
---

# Embedding-Amharic-Medium

This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [rasyosef/roberta-medium-amharic](https://huggingface.co/rasyosef/roberta-medium-amharic). It maps sentences & paragraphs to a 512-dimensional dense vector space and can be used for semantic textual similarity, semantic search, and information retrieval.

It was introduced in the paper [The Multilingual Curse at the Retrieval Layer: Evidence from Amharic](https://huggingface.co/papers/2605.24556).

- **Code:** [GitHub Repository](https://github.com/rasyosef/amharic-neural-ir)
- **Paper:** [The Multilingual Curse at the Retrieval Layer: Evidence from Amharic](https://huggingface.co/papers/2605.24556)

## Model Details

### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [rasyosef/roberta-medium-amharic](https://huggingface.co/rasyosef/roberta-medium-amharic)
- **Maximum Sequence Length:** 510 tokens
- **Output Dimensionality:** 512 dimensions
- **Similarity Function:** Cosine Similarity
- **Language:** am
- **License:** mit

### Full Model Architecture

```
SentenceTransformer(
  (0): Transformer({'max_seq_length': 510, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 512, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)
```

## Usage

### Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

```bash
pip install -U sentence-transformers
```

Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("rasyosef/embedding-amharic-medium")
# Run inference
sentences = [
    'ለውጭ ገበያ በሚቀርበው የኢትዮጵያ ቡና ላይ የተጋረጠው ፈተና',
    'የኢትዮጵያ ዋነኛ የውጭ ምንዛሬ ምንጭ የሆነው ወደ ውጭ የሚላክ ቡና ዘርፍ በአሁኑ ጊዜ ከፍተኛ ውጥረት ውስጥ ገብቷል። በዚህ የተነሳም የኢትዮጵያ ቡናና ሻይ ባለሥልጣንን ጨምሮ የሚመላካታቸው ሁሉ ቡና ላኪዎችና አምራቾች ያከማቹትን ቡና በፍጥነት ወደ ዓለም ገበያ እንዲያወጡ ጥሪ እያቀረቡ ነው ።',
    'የቻይናው ፕሬዝዳንት ዚ ጂንፒንግ ከትራምፕ ጋር ባደረጉት ጉባኤ ትኩረታቸው በሁለቱ ሀገራት መካከል ለወራት ከተፈጠረ ውጥረት እና የንግድ ጦርነት በኋላ የተረገጋጋ ግንኙነትን ማስቀጠል ነበር። ከፑቲን ጋር ደግሞ ዢ ለሁለቱ አገራት ስልታዊም ሆነ ኢኮኖሚያዊ ጠቀሜታ ረጅም ጊዜ የዘለቀውን አጋርነትን ይበልጥ ማጠናከር ላይ ነበር ትኩረታቸው።',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 512]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```

## Evaluation

### Metrics

#### Information Retrieval (dim 512)

| Metric              | Value      |
|:--------------------|:-----------|
| cosine_recall@5   | 0.8430     |
| cosine_recall@10  | 0.8883     |
| **cosine_ndcg@10**  | **0.7794** |
| cosine_mrr@10       | 0.7444     |

#### Information Retrieval (dim 256)

| Metric              | Value      |
|:--------------------|:-----------|
| cosine_recall@5   |  0.8409     |
| cosine_recall@10  | 0.8831     |
| **cosine_ndcg@10**  | **0.7736** |
| cosine_mrr@10       | 0.7382     |

## Training Details

<details>

### Training Dataset

* Size: 122,938 training samples
* Columns: <code>anchor</code>, <code>positive</code>, <code>negative_1</code>, and <code>negative_2</code>
* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
  ```json
  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          512,
          256
      ],
      "matryoshka_weights": [
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  ```

### Training Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 128
- `per_device_eval_batch_size`: 128
- `learning_rate`: 6e-05
- `num_train_epochs`: 6
- `lr_scheduler_type`: cosine
- `fp16`: True

### Framework Versions
- Python: 3.11.13
- Sentence Transformers: 4.1.0
- Transformers: 4.52.4
- PyTorch: 2.7.1+cu126

</details>

## Citation

```bibtex
@inproceedings{alemneh2026amharicir,
  title     = {The Multilingual Curse at the Retrieval Layer: Evidence from Amharic},
  author    = {Alemneh, Yosef Worku and Mekonnen, Kidist Amde and de Rijke, Maarten},
  booktitle = {Proceedings of the 1st Workshop on Multilinguality in the Era of Large Language Models (MeLLM), ACL 2026},
  year      = {2026},
}
```