Project AURIONAI Use-Cases Research & Innovation
embeddingfamily

BGE v1.5

English and Chinese text embedding models from BAAI's C-Pack work, for retrieval and semantic search; v1.5 improves the similarity distribution.

BAAIBAAIChina
BAAI
Levelfamily
Classembedding
Parametersnot in the notes
Contextnot in the notes
Released11 Sep 2023
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

20232024bge-base-en-v1.5bge-base-en-v1.5, Sep 2023bge-large-en-v1.5, Sep 2023bge-large-zh-v1.5, Sep 2023bge-small-en-v1.5, Sep 2023
BAAIbge-large-en-v1.5 belongs to this familyembedding12 Sep 2023335.14M
BAAIbge-large-zh-v1.5 belongs to this familyembedding12 Sep 2023
BAAIbge-small-en-v1.5 belongs to this familyembedding12 Sep 202333.36M
BAAIbge-base-en-v1.5 belongs to this familyembedding11 Sep 2023109.48M
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Retrieval-augmented generation (RAG)used byText embeddings for semantic searchproduced by

Identity

Developer
BAAI
Family
not in the notes
Released
11 Sep 2023 sourcesregistry date
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
Small, base and large sizes in English and Chinese; BGE-M3 and other BGE records already in AURION.
Context length
not in the notes
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
MIT License sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
Model card languages: en, zh
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2309.07597 https://arxiv.org/abs/2309.07597
  2. github.com/FlagOpen/FlagEmbedding https://github.com/FlagOpen/FlagEmbedding
  3. huggingface.co/api/models?pipeline_tag=feature-extraction&so... https://huggingface.co/api/models?pipeline_tag=feature-extraction&sort=downloads&limit=50
  4. jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
  5. huggingface.co/BAAI/bge-small-en-v1.5 https://huggingface.co/BAAI/bge-small-en-v1.5
  6. huggingface.co/BAAI/bge-base-en-v1.5 https://huggingface.co/BAAI/bge-base-en-v1.5

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "BGE v1.5", https://aurion.semai.id/models/baai-bge-v1-5/, records of October 2026.