SkillsHooksPromptsAgentsPersonasModelsPoliciesToolsTemplatesBundlesCategoriesStart here
← Models
Mo modeltext-generationaistable

reflection

A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

id model/reflectionvendor Matt Shumerfamily Reflection
Sizes
70b
Model card
https://ollama.com/library/reflection ↗

Providers

ProviderModel idGet itTagsPullsUpdated
Ollama ↗reflectionollama pull reflection17615.4K2024-09-09
ollamalocal
Author Matt Shumer. Source ollama.com/library (original ↗). License unknown — the source states none; review before redistributing. Imported 2026-09-03. Description, capabilities, sizes, pulls, tag count and updated date as shown on the Ollama library page. Vendor, family and task are inferred from the model name; weights license is not published on the listing.