Skip to content
← Models
Open weightsCyberAgent/10 trustMetrics-checked

CyberAgent OpenCalm 7B

Pioneering Japanese GPT-NeoX model released under CC BY-SA 4.0.

Visit official page →

About

OpenCalm-7B is CyberAgent's Japanese language model released in May 2023, built on the GPT-NeoX architecture with 6.8B parameters trained on Japanese Wikipedia and Common Crawl. It was among the first serious open Japanese LLMs and seeded a wave of domestic fine-tunes.

The model is released under Creative Commons Attribution-ShareAlike 4.0, a copyleft license that requires derivatives to share alike, so it suits research and open projects rather than proprietary products. CyberAgent later followed it with the Apache-licensed CALM2 series.

Specs

Context window

Pricing

Free quota

API access

Weights

Open weights

Released

May 1, 2023

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

japanese-nlpresearchfine-tuningopen-source-derivatives

Trust score — 7/10

/10 trustMetrics-checked

Scored 7/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 132; Trending score 66/100 from researcher assessment.

Sources