The Skywork-OR1 (Open Reasoner 1) model series consists of powerful math and code reasoning models
This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding.
ReadyArt/L3.3-The-Omega-Directive-70B-Unslop-v2.0 (Q4_K_M)
sophosympatheia/Midnight-Miqu-70B-v1.5 (i1-Q4_K_M)
This model was merged using the Model Stock merge method using nitky/Oumuamua-7b-base as a base.