metadata
base_model: Qwen/Qwen2.5-72B-Instruct
license: mit
datasets:
- arcee-ai/EvolKit-75K
- SkunkworksAI/reasoning-0.01
- berkeley-nest/Nectar
- Nexusflow/VirusTotalAgentic
- allenai/WildChat-1M-Full
- Magpie-Align/Magpie-LlamaCoT-250K
Experimental commander model V1.
Named it Zelensky in order to troll Uncle Elon on twitter over how bad Grok-2 is.
Training process, low 1 epoch learning rate and evolutionary-merged via https://github.com/arcee-ai/EvolKit
Process on 8x AMD Mi300 192GB gpus.
Thank you Vultr https://www.vultr.com/register/ for sponsoring the compute.
Qwen License applies by default.