# BAAI/bge-base-en

This model is an English text embedding model that maps text to low dimensional dense vectors. It can also be used in vector databases for LLMs after encoding text to dense vectors.

## Cite this

- Page: https://huggingbay.xyz/artifact/hf-model-baai-bge-base-en
- Citation: BAAI/bge-base-en. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-baai-bge-base-en (retrieved 2026-11-14).
- Check a downloaded file: run `shasum -a 256 <file>` (macOS), `sha256sum <file>` (Linux) or `Get-FileHash -Algorithm SHA256 <file>` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/files?limit=100. How checks work: https://huggingbay.xyz/verification

## Facts

- Type: Embedding
- Task: feature-extraction
- Framework: transformers
- License: mit: Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/MIT.html)
- Source: https://huggingface.co/BAAI/bge-base-en
- Hosting: hosted (18 files)
- Files: 18 hosted of 19 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 18 hosted of 19 listed
- Full repo upstream: 1.31 GB
- Recommended file: 438 MB · model.safetensors
- Download: https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/download-plan)
- Per-file SHA-256: available for 18 of 18 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/files?limit=100
- Availability: Ready
- Downloadable: yes
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 874883
- Stars: 73
- Card completeness: 93%

## Description

This model is an English text embedding model that maps text to low dimensional dense vectors. It can also be used in vector databases for LLMs after encoding text to dense vectors.

## Model Card Facts

- Declared license: mit
- Pipeline: feature-extraction
- Library: transformers
- Task categories: feature-extraction
- Languages: en
- Paper ids: 2310.07554, 2309.07597
- Model-index entries: bge-base-en
- Evaluation signals: 12 model-card eval results
- File hints: 16 upstream file samples

## Evaluation Signals

- MTEB AmazonCounterfactualClassification (en): accuracy = 75.73134328358209 (Classification)
- MTEB AmazonCounterfactualClassification (en): ap = 38.97277232632892 (Classification)
- MTEB AmazonCounterfactualClassification (en): f1 = 69.81740361139785 (Classification)
- MTEB AmazonPolarityClassification: accuracy = 92.56522500000001 (Classification)
- MTEB AmazonPolarityClassification: ap = 88.88821771869553 (Classification)
- MTEB AmazonPolarityClassification: f1 = 92.54817512659696 (Classification)
- MTEB AmazonReviewsClassification (en): accuracy = 46.91 (Classification)
- MTEB AmazonReviewsClassification (en): f1 = 46.28536394320311 (Classification)
- MTEB ArguAna: map_at_1 = 38.834 (Retrieval)
- MTEB ArguAna: map_at_10 = 53.564 (Retrieval)

## Referenced Data

- Paper: 2310.07554
- Paper: 2309.07597

## File Hints

- .gitattributes
- 1_Pooling/config.json
- README.md
- config.json
- config_sentence_transformers.json
- model.safetensors
- modules.json
- onnx/config.json
- onnx/model.onnx
- onnx/special_tokens_map.json
- onnx/tokenizer.json
- onnx/tokenizer_config.json

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-07-29T22:21:13.962Z.
- Open license detected as mit.
- Model-index metadata found for bge-base-en.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-baai-bge-base-en
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-baai-bge-base-en
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-baai-bge-base-en&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-baai-bge-base-en/decentralized-fallbacks