From the maker of Goliath(opens in new tab), Magnum 72B is the seventh in a family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet.
The model is based on Qwen2 72B(opens in new tab) and trained with 55 million tokens of highly curated roleplay (RP) data.
Modalities
Context
33K
Released
Sep 30, 2024
Knowledge Cutoff
Jun 2024
From the maker of Goliath, Magnum 72B is the seventh in a family of models designed to achieve the prose quality of the Claude 3 models, notably Opus & Sonnet. The model is based on Qwen2 72B and trained with 55 million tokens of highly curated roleplay (RP) data.
Magnum v2 72B has a 32,768 token context window.
Magnum v4 72B is another text model from the same author.
Magnum v2 72B was released on September 30, 2024. Its knowledge cutoff is June 30, 2024.
Token volume and request traffic to this model over time.