openthinker:7b

Upstream reference: OpenThinker 7B

Publisher: Open Thoughts

The publisher describes OpenThinker as a Qwen2.5-7B-Instruct fine-tune using the OpenThoughts-114k reasoning dataset derived from DeepSeek-R1 outputs.

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

Published upstream specifications

Base checkpoint

Qwen2.5-7B-Instruct Source

Training dataset

OpenThoughts-114k Source

Upstream derivative license label

Apache-2.0 Source

Publisher-described uses

• Reasoning-data and language-model research. Source

Reference limitations

• The base-model publisher, data-generation source and derivative publisher are separate roles; no model-equivalence claim follows from distilled data. Source

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

Publisher sources

• OpenThinker 7B official documentation — Open Thoughts. Checked 2026-11-02.

Links

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

• Open Thoughts — official developer/publisher
• Ollama
• Ollama
• Hugging Face
• GitHub (maker)

Where openthinker:7b comes from

Named in 1 observation page

• 3B-7B local models — all 53 · V1