olmo2:7b

Upstream reference: OLMo 2 November 2024 7B Instruct

Publisher: Allen Institute for AI

Ai2 documents an OLMo 2 text model post-trained through supervised tuning, preference optimization and reinforcement learning with verifiable rewards.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Published size label

7B Source

Upstream license label

Apache-2.0 Source

Documented training stages

SFT, DPO and RLVR Source

Publisher-described uses

• Language-model science and instruction-following text applications. Source

Reference limitations

• The card says post-trained models were replaced under the same names in January 2025, with the earlier artifacts retained as preview. Exact revision matters for historical identity. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• OLMo 2 November 2024 7B Instruct official documentation — Allen Institute for AI. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Allen Institute for AI — official site
• Ollama
• Provider page
• Hugging Face

Where olmo2:7b comes from

Named in 1 observation page

• 3B-7B local models — all 53 · V1