b

Sgpt Bloom 7b1 Msmarco

Aug 2022
bSgpt Bloom 7b1 Msmarco
Compare in
on
self-host onlyprice
39.5MTEB English v2
Aug 2022released
0K tokensMax input

Rankingconfiguration unstated?

Full ranking →
1Gemini Embedding 001832Jina Embeddings v5 Omni Small82.53Jina Embeddings v5 Text Small82.54Jina Embeddings v5 Omni Nano81.74Jina Embeddings v5 Text Nano81.7
···
44Bge Large En v1.567.745Sgpt Bloom 7b1 Msmarco67.446UAE Large v167.2

Strong at

C
Embeddings & Retrieval#150 of 200

Run it yourself

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

Benchmarks

in Embeddings & Retrieval
MTEB Persian v2 · Reranking · Persian33.8#96
JMTEB v2 · Clustering · Japanese12#130
JMTEB v2 · STS · Japanese57#117
LongEmbed · Mean over tasks · English28.6#132
LongEmbed · Mean over task types · English28.6#132
LongEmbed · Retrieval · English28.6#132
MTEB German v1 · Clustering · German11.9#138
MTEB German v1 · STS · German39.7#114
MTEB German v1 · Pair Classification · German52.8#48
MTEB German v1 · Reranking · German22.3#94
MTEB Europe v1 · Retrieval · multilingual (25 languages)31.5#110
MTEB Europe v1 · STS · multilingual (8 languages)62.7#61
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)37.9#122
MTEB Europe v1 · Clustering · multilingual (29 languages)27.5#144
MTEB Europe v1 · Instruction Reranking · English-3#163
MTEB Europe v1 · Pair Classification · multilingual (11 languages)80.1#113
MTEB Europe v1 · Reranking · multilingual (12 languages)45.2#136
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)5#158
MTEB French v1 · STS · French63.8#84
MTEB French v1 · Retrieval · multilingual (2 languages)31#94
MTEB French v1 · Reranking · French63.2#94
MTEB French v1 · Clustering · French32.4#97
MTEB French v1 · Summarization · French29.1#122
MTEB French v1 · Pair Classification · French63.5#43
MTEB Indic v1 · Retrieval · multilingual (14 languages)31#68
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)12.7#61
MTEB Indic v1 · Reranking · multilingual (2 languages)63.7#100
MTEB Indic v1 · Pair Classification · Hindi56.5#109
MTEB Indic v1 · STS · multilingual (13 languages)9.8#105
MTEB Indic v1 · Clustering · multilingual (21 languages)2.4#185
MTEB Korean v2 · STS · Korean50.9#47
MTEB Korean v2 · Reranking · Korean26.9#64
MTEB Korean v2 · Classification · Korean27.2#64
MTEB Dutch v1 · Reranking · Dutch64.2#186
MTEB Polish v1 · Pair Classification · Polish61.9#117
MTEB Polish v1 · STS · Polish47.5#108
MTEB Portuguese v1 · Multilabel Classification · Portuguese18.2#139
MTEB Law v1 · Mean over tasks · multilingual (3 languages)35.2#122
MTEB Law v1 · Mean over task types · multilingual (3 languages)35.2#122
MTEB Law v1 · Retrieval · multilingual (3 languages)35.2#122
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)38.9#70
MTEB Medical v1 · Mean over task types · multilingual (10 languages)39.5#48
MTEB Medical v1 · Retrieval · multilingual (10 languages)40.2#80
MTEB Medical v1 · Clustering · English26.4#212
MTEB Medical v1 · Reranking · Mandarin Chinese52#94
FollowIR · Mean over tasks · English-3#163
FollowIR · Mean over task types · English-3#163
FollowIR · Instruction Reranking · English-3#163
MTEB Spanish v1 · Pair Classification · Spanish60.1#103
MTEB Spanish v1 · STS · multilingual (2 languages)67.4#45
MTEB Spanish v1 · Clustering · Spanish35.6#104
MTEB Spanish v1 · Reranking · Spanish25.1#109
MTEB Thai v1 · Clustering · Thai1.3#194
MTEB Thai v1 · Pair Classification · Thai53.9#105
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)20.3#157
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)51.8#178
MTEB Russian v1.1 · STS · Russian40.4#105
MTEB Russian v1.1 · Reranking · Russian24.6#102
MTEB Russian v1.1 · Clustering · Russian16.2#116
MTEB Russian v1.1 · Pair Classification · Russian47.6#160
MTEB Russian v1.1 · Multilabel Classification · Russian25.1#144
RTEB French beta · Mean over tasks · multilingual (2 languages)20.4#128
RTEB German beta · Mean over tasks · German8.2#188
RTEB Law beta · Mean over tasks · multilingual (4 languages)23#183
MTEB multilingual v2 · Clustering · multilingual (208 languages)31.8#142
MTEB multilingual v2 · STS · multilingual (35 languages)57#89
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)72.3#109
MTEB multilingual v2 · Retrieval · multilingual (120 languages)35.3#126
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)29.9#100
MTEB multilingual v2 · Instruction Reranking · English-3#163
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)13.3#159
MTEB multilingual v2 · Reranking · multilingual (22 languages)43.5#123

FAQ

How much does Sgpt Bloom 7b1 Msmarco cost?›

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

Is Sgpt Bloom 7b1 Msmarco free to use?›

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

How good is Sgpt Bloom 7b1 Msmarco, and what is it best at?›

#150 of 200 in Embeddings.

Is Sgpt Bloom 7b1 Msmarco better than Bge Large En v1.5?›

On MTEB Spanish v1 · STS · multilingual (2 languages), Sgpt Bloom 7b1 Msmarco scores 67.4 vs 67.7 — about the same.

When was Sgpt Bloom 7b1 Msmarco released? Is there a newer version?›

Released 2022-08-26. It is the current version in its line.

Is Sgpt Bloom 7b1 Msmarco open source?›

Yes, the weights are open.

Can I run Sgpt Bloom 7b1 Msmarco locally?›

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

What is Sgpt Bloom 7b1 Msmarco?›

Sgpt Bloom 7b1 Msmarco is an open-weights embeddings & retrieval model from bigscience, released Aug 2022.

What are the best alternatives to Sgpt Bloom 7b1 Msmarco?›

Multilingual E5 Large Instruct (better), Jina Embeddings v5 Text Small (open weights).