# sonoisa/t5-base-japanese

Model from Hugging Face for feature extraction: sonoisa/t5-base-japanese · transformers

## Facts

- Type: Embedding
- Task: feature-extraction
- Framework: transformers
- License: cc-by-sa-4.0 — cc-by-sa-4.0: commercial use is permitted with attribution; adaptations must use the same or a permitted compatible license. (https://spdx.org/licenses/CC-by-sa-4.0.html)
- Source: https://huggingface.co/sonoisa/t5-base-japanese
- Hosting: hosted (5 files)
- Files: 5 hosted of 9 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: 5 files, 892.5 MB
- Full repo upstream: 2.68 GB
- Recommended file: 1.78 GB (2 files)
- Download: https://huggingbay.xyz/artifact/hf-model-sonoisa-t5-base-japanese/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-sonoisa-t5-base-japanese/download-plan)
- Per-file SHA-256: available for 5 of 5 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-sonoisa-t5-base-japanese/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: 42800
- Stars: 56
- Card completeness: 96%

## Description

External Hugging Face catalog record for sonoisa/t5-base-japanese. Task: feature extraction. Library: transformers. Languages: ja. Datasets referenced by card metadata: wikipedia, oscar, cc100. Popularity signal at import: 42,800 downloads and 56 likes.

## Model Card Facts

- Declared license: cc-by-sa-4.0
- Pipeline: feature-extraction
- Library: transformers
- Task categories: feature-extraction
- Languages: ja
- Referenced datasets: wikipedia, oscar, cc100
- File hints: 9 upstream file samples

## Referenced Data

- Dataset: wikipedia
- Dataset: oscar
- Dataset: cc100

## File Hints

- .gitattributes (790 B)
- README.md (4.9 KB)
- config.json (710 B)
- flax_model.msgpack (850 MB) LFS
- model.safetensors (850 MB) LFS
- pytorch_model.bin (850 MB) LFS
- special_tokens_map.json (1.7 KB)
- spiece.model (785 KB) LFS
- tokenizer_config.json (1.9 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 2026-09-21T06:53:51.075Z.
- Upstream license: cc-by-sa-4.0. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model card references dataset context: wikipedia, oscar, cc100.
- 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-sonoisa-t5-base-japanese
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-sonoisa-t5-base-japanese/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-sonoisa-t5-base-japanese/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-sonoisa-t5-base-japanese/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-sonoisa-t5-base-japanese
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-sonoisa-t5-base-japanese/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-sonoisa-t5-base-japanese&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-sonoisa-t5-base-japanese/decentralized-fallbacks