# ibm-granite/granite-embedding-278m-multilingual

Model from Hugging Face for sentence similarity: ibm-granite/granite-embedding-278m-multilingual · transformers

## Facts

- Type: Embedding
- Task: sentence-similarity
- Framework: transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/ibm-granite/granite-embedding-278m-multilingual
- Hosting: hosted (10 files)
- Files: 10 hosted of 13 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: 10 files, 570.9 MB
- Full repo upstream: 2.8 GB
- Recommended file: 2.78 GB (3 files)
- Parameters: 278M
- Download: https://huggingbay.xyz/artifact/hf-model-ibm-granite-granite-embedding-278m-multilingual/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-embedding-278m-multilingual/download-plan)
- Per-file SHA-256: available for 10 of 10 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-embedding-278m-multilingual/files?limit=100
- 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: 37961
- Stars: 85
- Card completeness: 96%

## Description

External Hugging Face catalog record for ibm-granite/granite-embedding-278m-multilingual. Task: sentence similarity. Library: transformers. Languages: en, ar, cs, de, es, fr, it, ja. Includes 12 model-card evaluation signals. Popularity signal at import: 39,002 downloads and 85 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: sentence-similarity
- Library: transformers
- Task categories: sentence-similarity
- Languages: en, ar, cs, de, es, fr, it, ja
- Paper ids: 2502.20204, 0000.00000
- Model-index entries: ibm-granite/granite-embedding-278m-multilingual
- Evaluation signals: 12 model-card eval results
- File hints: 13 upstream file samples

## Evaluation Signals

- MTEB AmazonCounterfactualClassification (en-ext): accuracy = 73.4333 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): f1 = 61.2301 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): f1_weighted = 78.40899999999999 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): ap = 23.347 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): ap_weighted = 23.347 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): main_score = 73.4333 (Classification)
- MTEB AmazonCounterfactualClassification (en): accuracy = 71.806 (Classification)
- MTEB AmazonCounterfactualClassification (en): f1 = 65.6467 (Classification)
- MTEB AmazonCounterfactualClassification (en): f1_weighted = 74.4815 (Classification)
- MTEB AmazonCounterfactualClassification (en): ap = 34.045700000000004 (Classification)

## Referenced Data

- Paper: 2502.20204
- Paper: 0000.00000

## File Hints

- .gitattributes (1.5 KB)
- 1_Pooling/config.json (191 B)
- README.md (596 KB)
- config.json (698 B)
- model.onnx (1.0 GB) LFS
- model.safetensors (530 MB) LFS
- modules.json (350 B)
- pytorch_model.bin (1.0 GB) LFS
- sentence_bert_config.json (54 B)
- sentencepiece.bpe.model (4.8 MB) LFS
- special_tokens_map.json (239 B)
- tokenizer.json (8.7 MB)

## 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 2026-07-29T22:21:36.619Z.
- Open license detected as apache-2.0.
- Model-index metadata found for ibm-granite/granite-embedding-278m-multilingual.
- 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-ibm-granite-granite-embedding-278m-multilingual
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-embedding-278m-multilingual/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-embedding-278m-multilingual/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-embedding-278m-multilingual/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-ibm-granite-granite-embedding-278m-multilingual
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-embedding-278m-multilingual/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-ibm-granite-granite-embedding-278m-multilingual&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-ibm-granite-granite-embedding-278m-multilingual/decentralized-fallbacks