Project AURIONAI Use-Cases Research & Innovation
embeddingfamily

GTE (General Text Embeddings)

Alibaba text embedding line trained with multi-stage contrastive learning, for retrieval, clustering and semantic similarity.

Alibaba (Qwen)Alibaba (Qwen)China
Alibaba (Qwen)
Levelfamily
Classembedding
Parametersnot in the notes
Contextnot in the notes
Released27 Jul 2023
Opennessunknown
Runs onnot in the notes
Statusactive

Lineage

202320242025gte-largegte-large, Jul 2023gte-small, Jul 2023gte-large-en-v1.5gte-large-en-v1.5, Apr 2024gte-Qwen2-7B-instructgte-Qwen2-7B-instruct, Jun 2024
Alibaba (Qwen)gte-Qwen2-7B-instruct belongs to this familyembedding15 Jun 20247.61B
Alibaba (Qwen)gte-large-en-v1.5 belongs to this familyembedding20 Apr 2024434.14M
Alibaba (Qwen)gte-large belongs to this familyembedding27 Jul 2023335.14M
Alibaba (Qwen)gte-small belongs to this familyembedding27 Jul 202333.36M
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
Alibaba (Qwen)
Family
not in the notes
Released
27 Jul 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
thenlper gte-small/base/large (2023), gte-v1.5 English (2024), gte-Qwen2 1.5B and 7B instruct LLM-based embedders; gte-multilingual-base is a separate AURION record.
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
unknown
Licence
not in the notes 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
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/2308.03281 https://arxiv.org/abs/2308.03281
  2. 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
  3. huggingface.co/api/models?pipeline_tag=sentence-similarity&s... https://huggingface.co/api/models?pipeline_tag=sentence-similarity&sort=downloads&limit=50
  4. huggingface.co/thenlper/gte-large https://huggingface.co/thenlper/gte-large
  5. huggingface.co/thenlper/gte-small https://huggingface.co/thenlper/gte-small

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GTE (General Text Embeddings)", https://aurion.semai.id/models/alibaba-gte/, records of October 2026.