# tomaarsen/splade-cocondenser-msmarco-margin-mse-small

Model from Hugging Face for feature extraction: tomaarsen/splade-cocondenser-msmarco-margin-mse-small · sentence transformers

## Facts

- Type: Embedding
- Task: feature-extraction
- 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/tomaarsen/splade-cocondenser-msmarco-margin-mse-small
- Hosting: hosted (8 files)
- Files: 8 hosted of 12 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, 438.8 MB
- Full repo upstream: 439.1 MB
- Recommended file: 438.1 MB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/download-plan)
- Per-file SHA-256: available for 8 of 8 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/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: 91
- Stars: 0
- Card completeness: 96%

## Description

External Hugging Face catalog record for tomaarsen/splade-cocondenser-msmarco-margin-mse-small. Task: feature extraction. Library: sentence transformers. Languages: en. Datasets referenced by card metadata: sentence-transformers/msmarco. Base model: Luyu/co-condenser-marco. Includes 12 model-card evaluation signals. Popularity signal at import: 91 downloads and 0 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: feature-extraction
- Library: sentence-transformers
- Base model: Luyu/co-condenser-marco
- Task categories: feature-extraction
- Languages: en
- Referenced datasets: sentence-transformers/msmarco
- Metrics: dot_accuracy@1, dot_accuracy@3, dot_accuracy@5, dot_accuracy@10, dot_precision@1, dot_precision@3, dot_precision@5, dot_precision@10
- Paper ids: 1908.10084, 2205.04733, 2010.02666, 2004.05665
- Model-index entries: CoCondenser trained on Natural-Questions tuples
- Evaluation signals: 12 model-card eval results
- File hints: 12 upstream file samples

## Evaluation Signals

- NanoMSMARCO: Dot Accuracy@1 = 0.46 (Sparse Information Retrieval)
- NanoMSMARCO: Dot Accuracy@3 = 0.64 (Sparse Information Retrieval)
- NanoMSMARCO: Dot Accuracy@5 = 0.72 (Sparse Information Retrieval)
- NanoMSMARCO: Dot Accuracy@10 = 0.82 (Sparse Information Retrieval)
- NanoMSMARCO: Dot Precision@1 = 0.46 (Sparse Information Retrieval)
- NanoMSMARCO: Dot Precision@3 = 0.21333333333333335 (Sparse Information Retrieval)
- NanoMSMARCO: Dot Precision@5 = 0.14400000000000002 (Sparse Information Retrieval)
- NanoMSMARCO: Dot Precision@10 = 0.08199999999999999 (Sparse Information Retrieval)
- NanoNFCorpus: Dot Accuracy@1 = 0.38 (Sparse Information Retrieval)
- NanoNFCorpus: Dot Accuracy@3 = 0.58 (Sparse Information Retrieval)

## Referenced Data

- Dataset: sentence-transformers/msmarco
- Paper: 1908.10084
- Paper: 2205.04733
- Paper: 2010.02666
- Paper: 2004.05665

## File Hints

- .gitattributes (1.5 KB)
- 1_SpladePooling/config.json (111 B)
- README.md (45 KB)
- config.json (649 B)
- config_sentence_transformers.json (292 B)
- model.safetensors (418 MB) LFS
- modules.json (287 B)
- sentence_bert_config.json (60 B)
- special_tokens_map.json (132 B)
- tokenizer.json (695 KB)
- tokenizer_config.json (1.3 KB)
- vocab.txt (226 KB)

## 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 2026-09-24T07:57:20.975Z.
- Open license detected as apache-2.0.
- Model-index metadata found for CoCondenser trained on Natural-Questions tuples.
- Model card references dataset context: sentence-transformers/msmarco.
- 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-tomaarsen-splade-cocondenser-msmarco-margin-mse-small
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-tomaarsen-splade-cocondenser-msmarco-margin-mse-small/decentralized-fallbacks