# allenai/Olmo-3-7B-Instruct-DPO

Model from Hugging Face for text generation: allenai/Olmo-3-7B-Instruct-DPO · 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/allenai/Olmo-3-7B-Instruct-DPO
- Hosting: hosted (10 files)
- Files: 10 hosted of 19 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, 14.6 GB
- Full repo upstream: 29.2 GB
- Recommended file: 29.2 GB (6 files)
- Parameters: 7B
- Download: https://huggingbay.xyz/artifact/hf-model-allenai-olmo-3-7b-instruct-dpo/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-allenai-olmo-3-7b-instruct-dpo/download-plan)
- Per-file SHA-256: available for 10 of 10 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-allenai-olmo-3-7b-instruct-dpo/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: 10604
- Stars: 3
- Card completeness: 96%

## Description

External Hugging Face catalog record for allenai/Olmo-3-7B-Instruct-DPO. Task: text generation. Library: transformers. Languages: en. Datasets referenced by card metadata: allenai/Dolci-Think-DPO-7B. Base model: allenai/Olmo-3-7B-Instruct-SFT. Popularity signal at import: 12,588 downloads and 3 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: text-generation
- Library: transformers
- Base model: allenai/Olmo-3-7B-Instruct-SFT
- Task categories: text-generation
- Languages: en
- Referenced datasets: allenai/Dolci-Think-DPO-7B
- Paper ids: 2512.13961
- File hints: 16 upstream file samples

## Referenced Data

- Dataset: allenai/Dolci-Think-DPO-7B
- Paper: 2512.13961

## File Hints

- .gitattributes (1.5 KB)
- README.md (11 KB)
- chat_template.jinja (2.6 KB)
- config.json (1.6 KB)
- generation_config.json (183 B)
- merges.txt (895 KB)
- model-00001-of-00003.safetensors (4.6 GB) LFS
- model-00002-of-00003.safetensors (4.6 GB) LFS
- model-00003-of-00003.safetensors (4.3 GB) LFS
- model.safetensors.index.json (30 KB)
- olmo-instruct.png (103 KB) LFS
- pytorch_model-00001-of-00003.bin (4.6 GB) LFS

## 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 2026-09-21T09:39:23.580Z.
- Upstream license: apache-2.0. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model card references dataset context: allenai/Dolci-Think-DPO-7B.
- 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-allenai-olmo-3-7b-instruct-dpo
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-allenai-olmo-3-7b-instruct-dpo/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-allenai-olmo-3-7b-instruct-dpo/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-allenai-olmo-3-7b-instruct-dpo/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-allenai-olmo-3-7b-instruct-dpo
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-allenai-olmo-3-7b-instruct-dpo/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-allenai-olmo-3-7b-instruct-dpo&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-allenai-olmo-3-7b-instruct-dpo/decentralized-fallbacks