# mabdulaziz499/bahith-arabic-retrieval-4b

Model from Hugging Face for sentence similarity: mabdulaziz499/bahith-arabic-retrieval-4b · sentence transformers

## 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/mabdulaziz499/bahith-arabic-retrieval-4b
- Hosting: hosted (8 files)
- Files: 8 hosted of 11 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: 8 files, 8.06 GB
- Full repo upstream: 8.06 GB
- Recommended file: 8.04 GB · model.safetensors
- Parameters: 4B
- Download: https://huggingbay.xyz/artifact/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/download-plan)
- Per-file SHA-256: available for 8 of 8 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/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: 87
- Stars: 1
- Card completeness: 96%

## Description

External Hugging Face catalog record for mabdulaziz499/bahith-arabic-retrieval-4b. Task: sentence similarity. Library: sentence transformers. Languages: ar. Datasets referenced by card metadata: miracl/miracl, castorini/mr-tydi. Base model: Qwen/Qwen3-Embedding-4B. Includes 4 model-card evaluation signals. Popularity signal at import: 87 downloads and 1 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: sentence-similarity
- Library: sentence-transformers
- Base model: Qwen/Qwen3-Embedding-4B
- Task categories: sentence-similarity
- Languages: ar
- Referenced datasets: miracl/miracl, castorini/mr-tydi
- Metrics: ndcg, mrr
- Model-index entries: bahith-arabic-retrieval-4b
- Evaluation signals: 4 model-card eval results
- File hints: 11 upstream file samples

## Evaluation Signals

- MTEB MIRACLRetrievalHardNegatives (ar): ndcg_at_10 = 0.7971 (Retrieval)
- MTEB MIRACLRetrievalHardNegatives (ar): mrr_at_10 = 0.8138 (Retrieval)
- MTEB SadeemQuestionRetrieval (default): ndcg_at_10 = 0.6933 (Retrieval)
- MTEB SadeemQuestionRetrieval (default): mrr_at_10 = 0.5842 (Retrieval)

## Referenced Data

- Dataset: miracl/miracl
- Dataset: castorini/mr-tydi

## File Hints

- .gitattributes (1.5 KB)
- 1_Pooling/config.json (96 B)
- README.md (7.5 KB)
- chat_template.jinja (2.4 KB)
- config.json (1.6 KB)
- config_sentence_transformers.json (376 B)
- model.safetensors (7.5 GB) LFS
- modules.json (429 B)
- sentence_bert_config.json (241 B)
- tokenizer.json (11 MB) LFS
- tokenizer_config.json (401 B)

## 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 2026-09-26T09:49:28.408Z.
- Open license detected as apache-2.0.
- Model-index metadata found for bahith-arabic-retrieval-4b.
- Model card references dataset context: miracl/miracl, castorini/mr-tydi.
- 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-mabdulaziz499-bahith-arabic-retrieval-4b
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-mabdulaziz499-bahith-arabic-retrieval-4b&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-mabdulaziz499-bahith-arabic-retrieval-4b/decentralized-fallbacks