# sail/Sailor-4B

Model from Hugging Face for text generation: sail/Sailor-4B · transformers

## Facts

- Type: LLM
- Task: text-generation
- 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/sail/Sailor-4B
- Hosting: hosted (10 files)
- Files: 10 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: 10 files, 7.91 GB
- Full repo upstream: 7.91 GB
- Recommended file: 7.9 GB · model.safetensors
- Parameters: 4B
- Download: https://huggingbay.xyz/artifact/hf-model-sail-sailor-4b/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-sail-sailor-4b/download-plan)
- Per-file SHA-256: available for 10 of 10 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-sail-sailor-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: 120
- Stars: 6
- Card completeness: 96%

## Description

External Hugging Face catalog record for sail/Sailor-4B. Task: text generation. Library: transformers. Languages: en, zh, id, th, vi, ms, lo. Datasets referenced by card metadata: cerebras/SlimPajama-627B, Skywork/SkyPile-150B, allenai/MADLAD-400, cc100. Base model: Qwen/Qwen1.5-4B. Includes 12 model-card evaluation signals. Popularity signal at import: 79 downloads and 6 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Base model: Qwen/Qwen1.5-4B
- Task categories: text-generation
- Languages: en, zh, id, th, vi, ms, lo
- Referenced datasets: cerebras/SlimPajama-627B, Skywork/SkyPile-150B, allenai/MADLAD-400, cc100
- Paper ids: 2404.03608
- Model-index entries: Sailor-4B
- Evaluation signals: 12 model-card eval results
- File hints: 12 upstream file samples

## Evaluation Signals

- XQuAD-Thai: EM (3-Shot) = 46.82 (text-generation)
- XQuAD-Thai: F1 (3-Shot) = 63.34 (text-generation)
- TyDiQA-Indonesian: EM (3-Shot) = 53.98 (text-generation)
- TyDiQA-Indonesian: F1 (3-Shot) = 73.48 (text-generation)
- XQuAD-Vietnamese: EM (3-Shot) = 47.65 (text-generation)
- XQuAD-Vietnamese: F1 (3-Shot) = 67.09 (text-generation)
- XCOPA-Thai: EM (3-Shot) = 53.4 (text-generation)
- XCOPA-Indonesian: EM (3-Shot) = 69.2 (text-generation)
- XCOPA-Vietnamese: EM (3-Shot) = 68.2 (text-generation)
- M3Exam-Thai: EM (3-Shot) = 27.88 (text-generation)

## Referenced Data

- Dataset: cerebras/SlimPajama-627B
- Dataset: Skywork/SkyPile-150B
- Dataset: allenai/MADLAD-400
- Dataset: cc100
- Paper: 2404.03608

## File Hints

- .gitattributes (1.5 KB)
- README.md (7.0 KB)
- added_tokens.json (80 B)
- banner_sailor.jpg (574 KB)
- config.json (662 B)
- generation_config.json (121 B)
- merges.txt (1.6 MB)
- model.safetensors (7.4 GB) LFS
- special_tokens_map.json (370 B)
- tokenizer.json (6.7 MB)
- tokenizer_config.json (1.1 KB)
- vocab.json (2.6 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 2026-09-03T18:27:54.777Z.
- Open license detected as apache-2.0.
- Model-index metadata found for Sailor-4B.
- Model card references dataset context: cerebras/SlimPajama-627B, Skywork/SkyPile-150B, allenai/MADLAD-400, 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-sail-sailor-4b
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-sail-sailor-4b/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-sail-sailor-4b/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-sail-sailor-4b/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-sail-sailor-4b
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-sail-sailor-4b/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-sail-sailor-4b&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-sail-sailor-4b/decentralized-fallbacks