m

Sentence Croissant Alpha v0.2

Mar 2024
mSentence Croissant Alpha v0.2
Compare in
on
self-host onlyprice
40.6MTEB English v2
Mar 2024released
2,048Dimensions
1K tokensMax input

Rankingconfiguration unstated?

Full ranking →
1Multilingual E5 Base332Rubert Tiny232.53Sentence Croissant Alpha v0.332.54Speed Embedding 7B Instruct32.45Bilingual Embedding Small32.3
···
71Nomic Embed Text v1.530.372Sentence Croissant Alpha v0.230.373Jina Embedding B En v130.2

Strong at

C
Embeddings & Retrieval#144 of 200

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
Licencenot verified

History

3 versions
303132Apr 24Release dateMTEB French · Summarizationv0.2v0.3v0.4
303132Apr 24Release dateMTEB French · Summarizationv0.2v0.3v0.4

Benchmarks

in Embeddings & Retrieval
MTEB Persian v2 · Reranking · Persian40.6#75
JMTEB v2 · Clustering · Japanese27.1#83
JMTEB v2 · STS · Japanese64.2#91
LongEmbed · Mean over tasks · English36.8#94
LongEmbed · Mean over task types · English36.8#94
LongEmbed · Retrieval · English36.8#94
MTEB German v1 · Mean over tasks · German46.8#38
MTEB German v1 · Mean over task types · German45.3#39
MTEB German v1 · Classification · German59.5#63
MTEB German v1 · Pair Classification · German53.9#41
MTEB German v1 · STS · German52.3#75
MTEB German v1 · Clustering · German28.5#57
MTEB German v1 · Retrieval · German42.4#45
MTEB German v1 · Reranking · German35.3#60
MTEB Europe v1 · Mean over tasks · multilingual (29 languages)49.2#40
MTEB Europe v1 · Mean over task types · multilingual (29 languages)44.2#37
MTEB Europe v1 · Classification · multilingual (23 languages)51.2#72
MTEB Europe v1 · Instruction Reranking · English-0.4#68
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)13.2#89
MTEB Europe v1 · STS · multilingual (8 languages)62#81
MTEB Europe v1 · Pair Classification · multilingual (11 languages)82.1#111
MTEB Europe v1 · Clustering · multilingual (29 languages)35.7#105
MTEB Europe v1 · Retrieval · multilingual (25 languages)41.9#81
MTEB Europe v1 · Reranking · multilingual (12 languages)51.5#94
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)60.8#94
MTEB French v1 · Retrieval · multilingual (2 languages)44.8#48
MTEB French v1 · Classification · French67.7#29
MTEB French v1 · Clustering · French37.4#79
MTEB French v1 · Reranking · French75.2#50
MTEB French v1 · Pair Classification · French67.3#15
MTEB French v1 · Summarization · French30.3#72
MTEB Indic v1 · Mean over tasks · multilingual (25 languages)36.6#64
MTEB Indic v1 · Mean over task types · multilingual (25 languages)26.5#66
MTEB Indic v1 · Classification · multilingual (8 languages)47.5#69
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)3.2#122
MTEB Indic v1 · STS · multilingual (13 languages)2.5#150
MTEB Indic v1 · Reranking · multilingual (2 languages)49.6#127
MTEB Indic v1 · Retrieval · multilingual (14 languages)20.6#84
MTEB Indic v1 · Pair Classification · Hindi57.5#106
MTEB Indic v1 · Clustering · multilingual (21 languages)4.5#111
MTEB Korean v2 · STS · Korean47.7#58
MTEB Korean v2 · Classification · Korean25.1#78
MTEB Korean v2 · Reranking · Korean16.6#78
MTEB Dutch v1 · Reranking · Dutch80.3#113
MTEB Polish v1 · Mean over tasks · Polish51.3#42
MTEB Polish v1 · Mean over task types · Polish50.8#44
MTEB Polish v1 · Classification · Polish49#66
MTEB Polish v1 · Clustering · Polish33.4#47
MTEB Polish v1 · STS · Polish55.5#83
MTEB Polish v1 · Pair Classification · Polish65.5#97
MTEB Portuguese v1 · Multilabel Classification · Portuguese13.3#197
MTEB Law v1 · Mean over tasks · multilingual (3 languages)42.3#71
MTEB Law v1 · Mean over task types · multilingual (3 languages)42.3#71
MTEB Law v1 · Retrieval · multilingual (3 languages)42.3#71
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)37.3#85
MTEB Medical v1 · Mean over task types · multilingual (10 languages)32.8#78
MTEB Medical v1 · Retrieval · multilingual (10 languages)39.4#85
MTEB Medical v1 · Clustering · English33.3#159
MTEB Medical v1 · Reranking · Mandarin Chinese25.8#117
FollowIR · Mean over tasks · English-0.4#68
FollowIR · Mean over task types · English-0.4#68
FollowIR · Instruction Reranking · English-0.4#68
MTEB Spanish v1 · STS · multilingual (2 languages)70.7#46
MTEB Spanish v1 · Clustering · Spanish44.6#42
MTEB Spanish v1 · Pair Classification · Spanish62.2#79
MTEB Spanish v1 · Reranking · Spanish42#70
MTEB Thai v1 · Pair Classification · Thai52.9#112
MTEB Thai v1 · Clustering · Thai4.8#119
MTEB Scandinavian v1 · Mean over tasks · multilingual (6 languages)45.5#66
MTEB Scandinavian v1 · Mean over task types · multilingual (6 languages)46.1#73
MTEB Scandinavian v1 · Classification · multilingual (6 languages)51#78
MTEB Scandinavian v1 · Retrieval · multilingual (3 languages)41#86
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)35.3#83
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)57#159
MTEB Russian v1.1 · Classification · Russian52.1#82
MTEB Russian v1.1 · Clustering · Russian45.6#84
MTEB Russian v1.1 · Reranking · Russian45#68
MTEB Russian v1.1 · Multilabel Classification · Russian27.2#98
MTEB Russian v1.1 · STS · Russian58.3#75
MTEB Russian v1.1 · Pair Classification · Russian52.9#108
RTEB French beta · Mean over tasks · multilingual (2 languages)26#112
RTEB German beta · Mean over tasks · German27#114
RTEB Law beta · Mean over tasks · multilingual (4 languages)33.6#119
MTEB multilingual v2 · Clustering · multilingual (208 languages)39.8#102
MTEB multilingual v2 · STS · multilingual (35 languages)57.5#87
MTEB multilingual v2 · Retrieval · multilingual (120 languages)36.5#121
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)15.3#129
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)32.2#95
MTEB multilingual v2 · Instruction Reranking · English-0.4#68
MTEB multilingual v2 · Reranking · multilingual (22 languages)50.9#86
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)72.2#112

FAQ

How much does Sentence Croissant Alpha v0.2 cost?›

There is no per-unit API price: self-host only.

Is Sentence Croissant Alpha v0.2 free to use?›

There is no free API. The weights are open, so you can run it yourself.

How good is Sentence Croissant Alpha v0.2, and what is it best at?›

#144 of 200 in Embeddings.

Is Sentence Croissant Alpha v0.2 better than Nomic Embed Text v1.5?›

On MTEB French v1 · Summarization · French, Sentence Croissant Alpha v0.2 scores 30.3 vs 30.3 — about the same.

When was Sentence Croissant Alpha v0.2 released? Is there a newer version?›

Released 2024-03-15. It is the current version in its line.

Is Sentence Croissant Alpha v0.2 open source?›

Yes, the weights are open.

Can I run Sentence Croissant Alpha v0.2 locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

What is Sentence Croissant Alpha v0.2?›

Sentence Croissant Alpha v0.2 is an open-weights embeddings & retrieval model from manu, released Mar 2024.

What are the best alternatives to Sentence Croissant Alpha v0.2?›

Multilingual E5 Base (better).