Skip to content

EthenEthenEthen

Open Source Model Profile · khoa-klaytn

bge-base-en-v1.5-angle

bge-base-en-v1.5-angle is a 109.48M-parameter BERT-family feature-extraction model from khoa-klaytn. It is configured for sentence-transformers embedding workflows.

Publisher
khoa-klaytn
Task
feature-extraction
Model type
bert
License
mit
Library
sentence-transformers
Publication status
Accepted · not indexed

Model overview

bge-base-en-v1.5-angle is published by khoa-klaytn as a feature-extraction model. The captured configuration identifies BertModel with model type bert, and Safetensors metadata reports about 109.48M parameters. The hub library is sentence-transformers, consistent with embedding use.

Recorded capabilities

BERT feature-extraction architecture

The captured configuration identifies BertModel with model type bert and sentence-transformers support.

Sentence-similarity tagging

Hub tags record feature-extraction with sentence-similarity, mteb, and text-embeddings-inference support.

Documented embedding usage

According to the model card, the publisher documents embedding use with Sentence-Transformers and Transformers, including CLS pooling and normalized embeddings.

Use cases in the source record

  • Sentence-embedding and retrieval workflows using the captured feature-extraction setup and documented Sentence-Transformers examples.
  • First-stage retrieval whose top-k outputs can be re-ranked, consistent with the publisher's described embedding-then-reranker pattern.

Limitations and unknowns

  • No evaluation results specific to this repository were extracted from this record.
  • No context-window or embedding-dimension value was extracted from this record.
  • Parts of the model card reproduce upstream BGE family history and leaderboard claims; those family-level statements were not treated as measurements of this repository.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: khoa-klaytn/bge-base-en-v1.5-angle

Captured: Unknown. Processed: 2026-09-07T19:34:49.026441+00:00.

FlagEmbedding Model List | FAQ | Usage | Evaluation | Train | Contact | Citation | License More details please refer to our Github: FlagEmbedding . English | 中文 FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs. ************* 🌟 Updates 🌟 ************* 10/12/2023: Release LLM-Embedder , a unified embedding model to support diverse retrieval augmentation needs for LLMs. Paper :fire: 09/15/2023: The technical report of BGE has been released 09/15/2023: The masive training data…

F001F002F003F004F005F006F007F008F009F010F015F016F018F024F025F028F029F030F031