Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · OrdalieTech

Solon-embeddings-large-0.1

Solon-embeddings-large-0.1 is a 559.89M-parameter French embedding model from OrdalieTech with a documented query-prefix format.

Publisher
OrdalieTech
Task
feature-extraction
Model type
xlm-roberta
License
mit
Library
transformers
Publication status
Approved for indexing

Model overview

Solon-embeddings-large-0.1 is published by OrdalieTech as a feature-extraction model. Safetensors metadata reports 559,890,432 parameters, with XLMRobertaModel and model type xlm-roberta. According to the model card, it is a French Solon large embedding release.

Recorded capabilities

French embedding focus

The model card introduces Solon large 0.1 as an open-source French embedding model.

Query instruction format

According to the model card, retrieval queries gain performance with a query : prefix, while passages need no instruction.

Publisher French-benchmark table

The model card reports a 0.7490 mean score across 9 French classification, reranking, and STS benchmarks, ahead of the listed multilingual alternatives.

Use cases in the source record

  • French passage retrieval in which queries carry the documented query : prefix for similarity search.
  • French classification, reranking, and STS evaluation of the kind listed in the publisher benchmark table.

Limitations and unknowns

  • Provider state is historical snapshot data, not independently refreshed current availability.
  • SOTA and benchmark-table figures are publisher-reported results and were not independently verified by Ethen.
  • No embedding dimension or context-window value was extracted from this record.

Source and provenance

Source: OrdalieTech/Solon-embeddings-large-0.1

Captured: Unknown. Processed: 2026-09-07T19:34:35.193921+00:00.

Solon Embeddings — large 0.1 SOTA Open source french embedding model. Instructions : Add "query : " before the query to retrieve to increase performance of retrieval. No instructions needed for passages . Model Mean Score OrdalieTech/Solon-embeddings-large-0.1 0.7490 cohere/embed-multilingual-v3 0.7402 OrdalieTech/Solon-embeddings-base-0.1 0.7306 openai/ada-002 0.7290 cohere/embed-multilingual-light-v3 0.6945 antoinelouis/biencoder-camembert-base-mmarcoFR 0.6826 dangvantuan/sentence-camembert-large 0.6756 voyage/voyage-01 0.6753 intfloat/multilingual-e5-large 0.6660 intfloat/multilingual-e5-base 0.6597 Sbert/paraphrase-multilingual-…

F001F002F003F004F005F006F007F009F010F011F012F013F014