# marin-community/marin-8b-base

Model from Hugging Face for text generation: marin-community/marin-8b-base · unknown

## Facts

- Type: LLM
- Task: text-generation
- Framework: unknown
- 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/marin-community/marin-8b-base
- Hosting: hosted (9 files)
- Files: 9 hosted of 10 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: 9 files, 32.1 GB
- Full repo upstream: 32.1 GB
- Recommended file: 32.1 GB (4 files)
- Parameters: 8B
- Download: https://huggingbay.xyz/artifact/hf-model-marin-community-marin-8b-base/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-marin-community-marin-8b-base/download-plan)
- Per-file SHA-256: available for 9 of 9 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-marin-community-marin-8b-base/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: 1309
- Stars: 17
- Card completeness: 96%

## Description

External Hugging Face catalog record for marin-community/marin-8b-base. Task: text generation. Library: unknown. Languages: en. Datasets referenced by card metadata: allenai/dolmino-mix-1124, allenai/olmo-mix-1124, bigcode/starcoderdata, EleutherAI/proof-pile-2, hltcoe/megawika, mlfoundations/dclm-baseline-1.0. Popularity signal at import: 3,282 downloads and 17 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: unknown
- Task categories: text-generation
- Languages: en
- Referenced datasets: allenai/dolmino-mix-1124, allenai/olmo-mix-1124, bigcode/starcoderdata, EleutherAI/proof-pile-2, hltcoe/megawika, mlfoundations/dclm-baseline-1.0, HuggingFaceTB/finemath, marin-community/ar5iv-noproblem-markdown
- Paper ids: 2109.01652, 1909.09436, 2110.14168, 2309.12284, 2310.03731, 2302.13971
- File hints: 10 upstream file samples

## Referenced Data

- Dataset: allenai/dolmino-mix-1124
- Dataset: allenai/olmo-mix-1124
- Dataset: bigcode/starcoderdata
- Dataset: EleutherAI/proof-pile-2
- Dataset: hltcoe/megawika
- Dataset: mlfoundations/dclm-baseline-1.0
- Dataset: HuggingFaceTB/finemath
- Dataset: marin-community/ar5iv-noproblem-markdown
- Dataset: marin-community/ar5iv-warning-markdown
- Dataset: marin-community/datashop-science-qa
- Dataset: marin-community/stackexchange-markdown
- Dataset: marin-community/wikipedia-markdown
- Paper: 2109.01652
- Paper: 1909.09436
- Paper: 2110.14168
- Paper: 2309.12284

## File Hints

- README.md (13 KB)
- config.json (2.0 KB)
- model-00001-of-00004.safetensors (9.2 GB) LFS
- model-00002-of-00004.safetensors (9.2 GB) LFS
- model-00003-of-00004.safetensors (7.7 GB) LFS
- model-00004-of-00004.safetensors (3.9 GB) LFS
- model.safetensors.index.json (22 KB)
- special_tokens_map.json (301 B)
- tokenizer.json (16 MB) LFS
- tokenizer_config.json (49 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 2026-09-22T04:21:34.567Z.
- Open license detected as apache-2.0.
- Model card references dataset context: allenai/dolmino-mix-1124, allenai/olmo-mix-1124, bigcode/starcoderdata, EleutherAI/proof-pile-2.
- 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-marin-community-marin-8b-base
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-marin-community-marin-8b-base/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-marin-community-marin-8b-base/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-marin-community-marin-8b-base/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-marin-community-marin-8b-base
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-marin-community-marin-8b-base/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-marin-community-marin-8b-base&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-marin-community-marin-8b-base/decentralized-fallbacks