Downloads · 30 days
346K
13% of all-time downloads
Solon-embeddings-large-0.1
OrdalieTech/Solon-embeddings-large-0.1
Solon-embeddings-large-0.1 is a feature extraction model from OrdalieTech. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as mit.
SOTA Open source french embedding model.
All-time downloads
2.6M
Public
Parameters
560M
9 GB on disk
Likes
55
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 99%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Dec 9, 2023
- Updated
- Mar 26, 2024
- SHA
- 9f6465f6
Model card
From the Hugging Face model README
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-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)
- Task
- Feature Extraction
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Languages
- fr
- Hf Inference
- live
- Created
- Dec 9, 2023
- Updated
- Mar 26, 2024