Model reference · open weights

roberta-amharic-text-embedding

Available as managed deployment Embeddings rasyosef · community Embeddings 1 variants 598 dl/mo

roberta-amharic-text-embedding is an open-weight embedding model from rasyosef. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byrasyosef
TypeEmbedding models
TaskEmbeddings
Parameters (lead)111M
Context512 tokens
Runs withsentence-transformers
Based onrasyosef/roberta-base-amharic
Released2025-01-04
Popularity598 downloads / month
LicenceOpen weights

About

What roberta-amharic-text-embedding is

This is a sentence-transformers model finetuned from rasyosef/roberta-base-amharic on the 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.

Read the full model card

Training Code

This model was trained as part of our ACL 2025 Findings paper: Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval.

  • Models Collection: https://huggingface.co/collections/rasyosef/amharic-text-embedding-models-679cb55eae1d498e3ac5bdc5
  • Code: https://github.com/kidist-amde/amharic-ir-benchmarks
  • Paper: https://arxiv.org/abs/2505.19356

Model Details

Model Description

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 510, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
  (1): Pooling({'word_embedding_dimension': 768, '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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("rasyosef/roberta-amharic-text-embedding-base")
# Run inference
sentences = [
  "የተደጋገመው የመሬት መንቀጥቀጥና የእሳተ ገሞራ ምልክት በአፋር ክልል",
  "በአክሱም ከተማ የሚገኙ ሙስሊም ሴት ተማሪዎች ከሒጃብ መልበስ ጋር በተያያዘ ውዝግብ ከትምህርት ገበታ ውጭ ሆነው እንደሚገኙ የትግራይ እስልምና ጉዳዮች ምክርቤት ስታወቀ። ይህን ለመፍታት ከክልሉ ትምህርት ቢሮ ጋር ንግግር ላይ መሆኑም የክልሉ እስልምና ጉዳዮች ምክርቤት ለዶቼቬለ ገልጿል።",
  "በማዕከላዊ ኢትዮጵያ ክልል ሃድያ ዞን ጊቤ ወረዳ በሚገኙ 12 ቀበሌዎች መሠረታዊ የመንግሥት አገልግሎት መስጫ ተቋማት በሙሉና በከፊል በመዘጋታቸው መቸገራቸውን ነዋሪዎች አመለከቱ። ከባለፈው ዓመት ጀምሮ የጤና፣ የትምህርት እና የግብር አሰባሰብ ሥራዎች በየአካባቢያቸው እየተከናወኑ አለመሆናቸውንም ለዶቼ ቬለ ተናግረዋል።",
  "የሕዝብ ተወካዮች ምክር ቤት አባል እና የቋሚ ኮሚቴ ሰብሳቢ የነበሩት አቶ ክርስቲያን ታደለ እና የአማራ ክልል ምክር ቤት አባል የሆኑት አቶ ዮሐንስ ቧያለው ከቃሊቲ ወደ ቂሊንጦ ማረሚያ ቤት መዛወራቸውን ጠበቃቸው ተናገሩ።",
  "ከተደጋጋሚ መሬት መንቀጥቀጥ በኋላ አፋር ክልል እሳት ከመሬት ውስጥ ሲፈላ ታይቷል፡፡ ከመሬት ውስጥ እሳትና ጭስ የሚተፋው እንፋሎቱ ዛሬ ማለዳውን 11 ሰዓት ግድም ከከባድ ፍንዳታ በኋላየተስተዋለ መሆኑን የአከባቢው ነዋሪዎች እና ባለስልጣናት ለዶቼ ቬለ ተናግረዋል፡፡ አለት የሚያፈናጥር እሳት ነው የተባለው እንፋሎቱ በክልሉ ጋቢረሱ (ዞን 03) ዱለቻ ወረዳ ሰጋንቶ ቀበሌ መከሰቱን የገለጹት የአከባቢው የአይን እማኞች ከዋናው ፍንዳታ በተጨማሪ በዙሪያው ተጨማሪ ፍንዳታዎች መታየት ቀጥሏል ባይ ናቸው፡፡"
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [5, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [5, 5]

Evaluation

Metrics

Information Retrieval
MetricValue
cosine_accuracy@10.7023
cosine_accuracy@30.8336
cosine_accuracy@50.8712
cosine_accuracy@100.913
cosine_precision@10.7023
cosine_precision@30.2779
cosine_precision@50.1742
cosine_precision@100.0913
cosine_recall@10.7023
cosine_recall@30.8336
cosine_recall@50.8712
cosine_recall@100.913
cosine_ndcg@100.8083
cosine_mrr@100.7747
cosine_map@1000.7777
Information Retrieval
MetricValue
cosine_accuracy@10.6951
cosine_accuracy@30.8251
cosine_accuracy@50.8649
cosine_accuracy@100.9072
cosine_precision@10.6951
cosine_precision@30.275
cosine_precision@50.173
cosine_precision@100.0907
cosine_recall@10.6951
cosine_recall@30.8251
cosine_recall@50.8649
cosine_recall@100.9072
cosine_ndcg@100.8024
cosine_mrr@100.7686
cosine_map@1000.7719

Training Details

Training Dataset

amharic-news-retrieval-dataset

From the published model card. Full card on the HuggingFace links in the sidebar.

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Information Retrievaldim 768Cosine Accuracy@10.702
Information Retrievaldim 768Cosine Accuracy@30.834
Information Retrievaldim 768Cosine Accuracy@50.871
Information Retrievaldim 768Cosine Accuracy@100.913
Information Retrievaldim 768Cosine Precision@10.702
Information Retrievaldim 768Cosine Precision@30.278
Information Retrievaldim 768Cosine Precision@50.174
Information Retrievaldim 768Cosine Precision@100.091
Information Retrievaldim 768Cosine Recall@10.702
Information Retrievaldim 768Cosine Recall@30.834
Information Retrievaldim 768Cosine Recall@50.871
Information Retrievaldim 768Cosine Recall@100.913
Information Retrievaldim 768Cosine Ndcg@100.808
Information Retrievaldim 768Cosine Mrr@100.775
Information Retrievaldim 768Cosine Map@1000.778
Information Retrievaldim 256Cosine Accuracy@10.695
Information Retrievaldim 256Cosine Accuracy@30.825
Information Retrievaldim 256Cosine Accuracy@50.865
Information Retrievaldim 256Cosine Accuracy@100.907
Information Retrievaldim 256Cosine Precision@10.695
Information Retrievaldim 256Cosine Precision@30.275
Information Retrievaldim 256Cosine Precision@50.173
Information Retrievaldim 256Cosine Precision@100.091
Information Retrievaldim 256Cosine Recall@10.695

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys roberta-amharic-text-embedding for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (roberta-amharic-text-embedding below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"roberta-amharic-text-embedding","input":"text to embed"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms