marcuscedricridia/Hush-Qwen2.5-7B-RP-v1.3
Partial fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1. Partial change: 50% of the weights changed (attention, mlp), in 28 of 28 layers.
Tensors changed: Norms 0/57, MLP 42/84, Attention 98/196
1 derivatives checked
- mradermacher/Hush-Qwen2.5-7B-RP-v1.3-GGUF: Same weights, converted