s

Text2vec Base Chinese Paraphrase

Jun 2023
sText2vec Base Chinese Paraphrase
Compare in
on
price not verifiedprice
32.3MTEB Medical v1
Jun 2023released
768Dimensions
0K tokensMax input
zhLanguages

Ranking?

Full ranking →
1F2LLM 4B71.12F2LLM 1.7B60.33F2LLM v2 14B57.64F2LLM v2 8B55.95F2LLM v2 4B55.5
···
172Multilingual E5 Base32.4173Text2vec Base Chinese Paraphrase32.3174Bge M332.2

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
LicenceApache-2.0free for commercial use

Benchmarks

in Embeddings & Retrieval
BEIR · Mean over tasks · English24.7#176
BEIR · Mean over task types · English24.7#176
BEIR · Retrieval · English24.7#176
MTEB Persian v2 · Reranking · Persian43.9#68
JMTEB v2 · Clustering · Japanese28.4#73
JMTEB v2 · STS · Japanese79#52
LongEmbed · Mean over tasks · English17.9#154
LongEmbed · Mean over task types · English17.9#154
LongEmbed · Retrieval · English17.9#154
MTEB German v1 · Mean over tasks · German42.9#43
MTEB German v1 · Mean over task types · German42.4#41
MTEB German v1 · Clustering · German21.7#107
MTEB German v1 · Retrieval · German29.9#80
MTEB German v1 · Classification · German57.2#65
MTEB German v1 · STS · German65.6#41
MTEB German v1 · Pair Classification · German54.7#26
MTEB German v1 · Reranking · German25.5#83
MTEB Europe v1 · Retrieval · multilingual (25 languages)28.7#116
MTEB Europe v1 · STS · multilingual (8 languages)74.3#16
MTEB Europe v1 · Bitext Mining · multilingual (28 languages)75#90
MTEB Europe v1 · Clustering · multilingual (29 languages)30.7#137
MTEB Europe v1 · Instruction Reranking · English-4#194
MTEB Europe v1 · Pair Classification · multilingual (11 languages)86.1#46
MTEB Europe v1 · Reranking · multilingual (12 languages)42.9#145
MTEB Europe v1 · Multilabel Classification · multilingual (23 languages)4.2#163
MTEB French v1 · Retrieval · multilingual (2 languages)28.3#99
MTEB French v1 · Reranking · French59.2#103
MTEB French v1 · Clustering · French33#96
MTEB French v1 · Summarization · French29.3#112
MTEB French v1 · Pair Classification · French65.3#27
MTEB Indic v1 · Retrieval · multilingual (14 languages)29.4#69
MTEB Indic v1 · Bitext Mining · multilingual (20 languages)6.8#73
MTEB Indic v1 · Reranking · multilingual (2 languages)53.7#118
MTEB Indic v1 · Pair Classification · Hindi69.9#59
MTEB Indic v1 · STS · multilingual (13 languages)19.4#86
MTEB Indic v1 · Clustering · multilingual (21 languages)9.3#101
MTEB Korean v2 · STS · Korean63#44
MTEB Korean v2 · Reranking · Korean24#65
MTEB Korean v2 · Classification · Korean40.4#60
MTEB Dutch v1 · Mean over tasks · Dutch40.6#81
MTEB Dutch v1 · Mean over task types · Dutch51.3#66
MTEB Dutch v1 · Classification · Dutch53.1#69
MTEB Dutch v1 · Clustering · Dutch22.3#87
MTEB Dutch v1 · Retrieval · Dutch28#102
MTEB Dutch v1 · STS · Dutch80#27
MTEB Dutch v1 · Multilabel Classification · Dutch30#88
MTEB Dutch v1 · Pair Classification · Dutch76.9#38
MTEB Dutch v1 · Reranking · Dutch69.1#180
MTEB Polish v1 · Pair Classification · Polish83.6#31
MTEB Polish v1 · Classification · Polish49.7#59
MTEB Portuguese v1 · Multilabel Classification · Portuguese20.6#65
MTEB Law v1 · Mean over tasks · multilingual (3 languages)30.6#138
MTEB Law v1 · Mean over task types · multilingual (3 languages)30.6#138
MTEB Law v1 · Retrieval · multilingual (3 languages)30.6#138
MTEB Medical v1 · Mean over tasks · multilingual (10 languages)32.2#94
MTEB Medical v1 · Mean over task types · multilingual (10 languages)37.1#51
MTEB Medical v1 · Retrieval · multilingual (10 languages)30.4#103
MTEB Medical v1 · Clustering · English32.3#173
MTEB Medical v1 · Reranking · Mandarin Chinese48.6#98
FollowIR · Mean over tasks · English-4#194
FollowIR · Mean over task types · English-4#194
FollowIR · Instruction Reranking · English-4#194
MTEB Spanish v1 · Pair Classification · Spanish70.6#31
MTEB Spanish v1 · Clustering · Spanish37.4#94
MTEB Spanish v1 · Reranking · Spanish36.8#83
MTEB Thai v1 · Clustering · Thai23.8#103
MTEB Thai v1 · Pair Classification · Thai73.1#47
MTEB Scandinavian v1 · Clustering · multilingual (2 languages)29.2#121
MTEB Scandinavian v1 · Bitext Mining · multilingual (3 languages)48.7#191
MTEB Russian v1.1 · Classification · Russian51.5#83
MTEB Russian v1.1 · Reranking · Russian38.6#76
MTEB Russian v1.1 · Clustering · Russian44.3#81
MTEB Russian v1.1 · Pair Classification · Russian54.6#94
MTEB Russian v1.1 · Multilabel Classification · Russian29.4#79
RTEB Finnish beta · Mean over tasks · English16.8#94
RTEB French beta · Mean over tasks · multilingual (2 languages)15.8#145
RTEB German beta · Mean over tasks · German11.7#173
RTEB Health beta · Mean over tasks · multilingual (4 languages)21#81
RTEB Law beta · Mean over tasks · multilingual (4 languages)21.4#191
MTEB multilingual v2 · Clustering · multilingual (208 languages)35.3#131
MTEB multilingual v2 · STS · multilingual (35 languages)69.3#57
MTEB multilingual v2 · Pair Classification · multilingual (24 languages)77.8#59
MTEB multilingual v2 · Retrieval · multilingual (120 languages)27#152
MTEB multilingual v2 · Bitext Mining · multilingual (1026 languages)39.5#90
MTEB multilingual v2 · Instruction Reranking · English-4#194
MTEB multilingual v2 · Multilabel Classification · multilingual (25 languages)14.2#147
MTEB multilingual v2 · Reranking · multilingual (22 languages)46.3#105
MTEB German v1 · Clustering · German · Text2Vec Base Chinese Paraphrase / USER BGE-M38.1#2
MTEB German v1 · Classification · German · Stella Large Chinese v3 · 1792 dimensions / Text2Vec Base Chinese Paraphrase / USER BGE-M342.3#3
MTEB German v1 · Pair Classification · German · Text2Vec Base Chinese Paraphrase / USER BGE-M351.3#2

FAQ

How much does Text2vec Base Chinese Paraphrase cost?›

There is no per-unit API price: price not verified.

How good is Text2vec Base Chinese Paraphrase, and what is it best at?›

#162 of 220 in Embeddings.

Is Text2vec Base Chinese Paraphrase better than Multilingual E5 Base?›

On MTEB Medical v1 · Clustering · English, Text2vec Base Chinese Paraphrase scores 32.3 vs 32.4 — about the same.

When was Text2vec Base Chinese Paraphrase released? Is there a newer version?›

Released 2023-06-22. It is the current version in its line.

Is Text2vec Base Chinese Paraphrase open source?›

Yes, the weights are open (Apache-2.0 licence).

Can I run Text2vec Base Chinese Paraphrase locally?›

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

What is Text2vec Base Chinese Paraphrase?›

Text2vec Base Chinese Paraphrase is an open-weights embeddings & retrieval model from shibing624, released Jun 2023.

What are the best alternatives to Text2vec Base Chinese Paraphrase?›

EmbeddingGemma 300M (better), F2LLM 4B (open weights).