metadata
pipeline_tag: sentence-similarity
tags:
- feature-extraction
license: mit
language:
- fr
- en
model-index:
- name: Solon-embeddings-base-0.1
results:
- task:
type: sentence-similarity
name: Passage Retrieval
dataset:
type: unicamp-dl/mmarco
name: mMARCO-fr
config: french
split: validation
metrics:
- type: recall_at_500
name: Recall@500
value: 90.9
- type: recall_at_100
name: Recall@100
value: 80.6
- type: recall_at_10
name: Recall@10
value: 52.5
- type: map_at_10
name: MAP@10
value: 27.4
- type: ndcg_at_10
name: nDCG@10
value: 33.5
- type: mrr_at_10
name: MRR@10
value: 27.9
Solon Embeddings — Base 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-mpnet-base-v2 | 0.5975 |
| dangvantuan/sentence-camembert-base | 0.5456 |
| EuropeanParliament/eubert_embedding_v1 | 0.5063 |
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)