CoolFace
Modelpublic

OrdalieTech/Solon-embeddings-large-0.1

sourceHugging Facemitupdated 2y agoView on Hugging Face
55likes347kdownloads
Model Card

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.

ModelMean Score
OrdalieTech/Solon-embeddings-large-0.10.7490
cohere/embed-multilingual-v30.7402
OrdalieTech/Solon-embeddings-base-0.10.7306
openai/ada-0020.7290
cohere/embed-multilingual-light-v30.6945
antoinelouis/biencoder-camembert-base-mmarcoFR0.6826
dangvantuan/sentence-camembert-large0.6756
voyage/voyage-010.6753
intfloat/multilingual-e5-large0.6660
intfloat/multilingual-e5-base0.6597
Sbert/paraphrase-multilingual-mpnet-base-v20.5975
dangvantuan/sentence-camembert-base0.5456
EuropeanParliament/eubertembeddingv10.5063

These results have been obtained through 9 french benchmarks on a variety of text similarity tasks (classification, reranking, STS) :

  • AmazonReviewsClassification (MTEB)
  • MassiveIntentClassification (MTEB)
  • MassiveScenarioClassification (MTEB)
  • MTOPDomainClassification (MTEB)
  • MTOPIntentClassification (MTEB)
  • STS22 (MTEB)
  • MiraclFRRerank (Miracl)
  • OrdalieFRSTS (Ordalie)
  • OrdalieFRReranking (Ordalie)

We created OrdalieFRSTS and OrdalieFRReranking to enhance the benchmarking capabilities of French STS and reranking assessments.

(evaluation script available here : github.com/OrdalieTech/mteb)