KaraKaraWitch/SteyrCannon-0.2-Qwen2.5-72b

KaraKaraWitch/SteyrCannon-0.2-Qwen2.5-72b is a 72.7 billion parameter language model merge, built upon the Qwen2.5 architecture with a 131072 token context length. Created using the TIES merge method, it combines anthracite-org/magnum-v4-72b and EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2, using the latter as its base. This model is designed for general language tasks, leveraging the strengths of its merged components.

Warm
Public
72.7B
FP8
131072
Hugging Face

No reviews yet. Be the first to review!