# ATH-MaaS/Marco-Nano-Instruct

Model from Hugging Face for text generation: ATH-MaaS/Marco-Nano-Instruct · 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/ATH-MaaS/Marco-Nano-Instruct
- Hosting: hosted (11 files)
- Files: 11 hosted of 13 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: 11 files, 16 GB
- Full repo upstream: 16 GB
- Recommended file: 16 GB (3 files)
- Download: https://huggingbay.xyz/artifact/hf-model-ath-maas-marco-nano-instruct/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-ath-maas-marco-nano-instruct/download-plan)
- Per-file SHA-256: available for 11 of 11 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-ath-maas-marco-nano-instruct/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: 510
- Stars: 42
- Card completeness: 96%

## Description

External Hugging Face catalog record for ATH-MaaS/Marco-Nano-Instruct. Task: text generation. Library: transformers. Languages: en, zh, ar, de, es, fr, ko, ja. Datasets referenced by card metadata: allenai/Dolci-Instruct-SFT, nvidia/Nemotron-Cascade-2-SFT-Data, nvidia/Nemotron-RL-instruction_following, nvidia/Nemotron-RL-instruction_following-structured_outputs, nvidia/Nemotron-RL-ReasoningGym-v1, nvidia/Nemotron-RL-knowledge-mcqa. Popularity signal at import: 1,456 downloads and 42 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Task categories: text-generation
- Languages: en, zh, ar, de, es, fr, ko, ja
- Referenced datasets: allenai/Dolci-Instruct-SFT, nvidia/Nemotron-Cascade-2-SFT-Data, nvidia/Nemotron-RL-instruction_following, nvidia/Nemotron-RL-instruction_following-structured_outputs, nvidia/Nemotron-RL-ReasoningGym-v1, nvidia/Nemotron-RL-knowledge-mcqa, nvidia/Nemotron-Cascade-RL-RLHF, BytedTsinghua-SIA/DAPO-Math-17k
- File hints: 13 upstream file samples

## Referenced Data

- Dataset: allenai/Dolci-Instruct-SFT
- Dataset: nvidia/Nemotron-Cascade-2-SFT-Data
- Dataset: nvidia/Nemotron-RL-instruction_following
- Dataset: nvidia/Nemotron-RL-instruction_following-structured_outputs
- Dataset: nvidia/Nemotron-RL-ReasoningGym-v1
- Dataset: nvidia/Nemotron-RL-knowledge-mcqa
- Dataset: nvidia/Nemotron-Cascade-RL-RLHF
- Dataset: BytedTsinghua-SIA/DAPO-Math-17k
- Dataset: Skywork/Skywork-OR1-RL-Data
- Dataset: nvidia/Nemotron-SFT-Multilingual-v1

## File Hints

- .gitattributes (1.5 KB)
- README.md (8.3 KB)
- config.json (1000 B)
- configuration.json (48 B)
- generation_config.json (121 B)
- model-00000-of-00003.safetensors (5.0 GB) LFS
- model-00001-of-00003.safetensors (5.0 GB) LFS
- model-00002-of-00003.safetensors (4.9 GB) LFS
- model.safetensors.index.json (1.7 MB)
- technical_details.pdf (1.9 MB) LFS
- tokenizer.json (6.7 MB)
- tokenizer_config.json (8.0 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 2026-08-29T15:33:53.704Z.
- Open license detected as apache-2.0.
- Model card references dataset context: allenai/Dolci-Instruct-SFT, nvidia/Nemotron-Cascade-2-SFT-Data, nvidia/Nemotron-RL-instruction_following, nvidia/Nemotron-RL-instruction_following-structured_outputs.
- 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-ath-maas-marco-nano-instruct
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-ath-maas-marco-nano-instruct/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-ath-maas-marco-nano-instruct/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-ath-maas-marco-nano-instruct/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-ath-maas-marco-nano-instruct
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-ath-maas-marco-nano-instruct/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-ath-maas-marco-nano-instruct&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-ath-maas-marco-nano-instruct/decentralized-fallbacks