---
base_model:
- Qwen/Qwen2.5-72B-Instruct
- huihui-ai/Qwen2.5-72B-Instruct-abliterated
- Qwen/Qwen2.5-72B
- spow12/ChatWaifu_72B_v2.2
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 with the 3 other models(listed on modelcard)

Process repeated multiple times on 8x AMD Mi300 192GB gpus while also running gpqa_diamond_zeroshot on LM_Eval harness.

Thank you Vultr https://www.vultr.com/register/ for sponsoring the compute.


Qwen License still applies by default.