# Alibaba-NLP/gte-multilingual-base This model is a multilingual text embedding model with an encoder only transformer architecture, 768 dimensional outputs, and input lengths up to 8192 tokens. It supports more than 70 languages and can produce both dense embeddings and sparse vectors for retrieval and text representation tasks. ## Cite this - Page: https://huggingbay.xyz/artifact/hf-model-alibaba-nlp-gte-multilingual-base - Citation: Alibaba-NLP/gte-multilingual-base. The Hugging Bay model record. https://huggingbay.xyz/artifact/hf-model-alibaba-nlp-gte-multilingual-base (retrieved 2026-11-14). - Check a downloaded file: run `shasum -a 256 ` (macOS), `sha256sum ` (Linux) or `Get-FileHash -Algorithm SHA256 ` (Windows), then compare with that file's SHA-256 at https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/files?limit=100. How checks work: https://huggingbay.xyz/verification ## Facts - Type: Embedding - Task: sentence-similarity - Framework: sentence-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/Alibaba-NLP/gte-multilingual-base - Hosting: hosted (1 file) - Files: 1 hosted of 8 listed - Needs its own code to run: Tagged custom_code on its source page. Plain llama.cpp, Ollama and LM Studio commands are not offered for this model unless a GGUF file is 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: 1 hosted of 8 listed - Full repo upstream: 629.6 MB - Download: https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/download-plan (download plan: https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/download-plan) - Per-file SHA-256: available for 1 of 1 hosted file via https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/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: 1214783 - Stars: 391 - Card completeness: 93% ## Description This model is a multilingual text embedding model with an encoder only transformer architecture, 768 dimensional outputs, and input lengths up to 8192 tokens. It supports more than 70 languages and can produce both dense embeddings and sparse vectors for retrieval and text representation tasks. ## Model Card Facts - Declared license: apache-2.0 - Pipeline: sentence-similarity - Library: sentence-transformers - Task categories: sentence-similarity - Languages: af, ar, az, be, bg, bn, ca, ceb - Paper ids: 2407.19669, 2210.09984, 2402.03216, 2007.15207, 2104.08663, 2402.07440 - Model-index entries: gte-multilingual-base (dense) - Evaluation signals: 12 model-card eval results - File hints: 16 upstream file samples ## Evaluation Signals - MTEB 8TagsClustering: v_measure = 33.66681726329994 (Clustering) - MTEB AFQMC: cos_sim_spearman = 43.54760696384009 (STS) - MTEB ATEC: cos_sim_spearman = 48.91186363417501 (STS) - MTEB AllegroReviews: accuracy = 41.689860834990064 (Classification) - MTEB AlloProfClusteringP2P: v_measure = 54.20241337977897 (Clustering) - MTEB AlloProfClusteringS2S: v_measure = 44.34083695608643 (Clustering) - MTEB AlloprofReranking: map = 64.91495250072002 (Reranking) - MTEB AlloprofRetrieval: ndcg_at_10 = 53.638 (Retrieval) - MTEB AmazonCounterfactualClassification (en): accuracy = 75.95522388059702 (Classification) - MTEB AmazonPolarityClassification: accuracy = 80.717625 (Classification) ## Referenced Data - Paper: 2407.19669 - Paper: 2210.09984 - Paper: 2402.03216 - Paper: 2007.15207 - Paper: 2104.08663 - Paper: 2402.07440 ## File Hints - .gitattributes - 1_Pooling/config.json - README.md - config.json - images/mgte-loco.png - images/mgte-mldr.png - images/mgte-mteb.png - images/mgte-reranker.png - images/mgte-retrieval.png - model.safetensors - modules.json - scripts/gte_embedding.py ## 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 - Reviewed large mirror worker mirrored 10 Hugging Face files by reviewed-large-mirror-worker; 0 medium-risk weight files used explicit admin review. - External catalog metadata imported from Hugging Face public API on 2026-07-11T16:49:22.989Z. - Open license detected as apache-2.0. - Model-index metadata found for gte-multilingual-base (dense). - 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-alibaba-nlp-gte-multilingual-base - Files API: https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/files?limit=100 - Metadata: https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/metadata.json - Distribution: https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/distribution - Manifest: https://huggingbay.xyz/api/manifests/hf-model-alibaba-nlp-gte-multilingual-base - Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/download-plan - Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-alibaba-nlp-gte-multilingual-base&limit=100 - Request mirror: not applicable. - Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-alibaba-nlp-gte-multilingual-base/decentralized-fallbacks