Sorawiz/Qwen2.5-14B-Instinct-RP
Full fine-tune vs Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336
2 derivatives checked
- mradermacher/Qwen2.5-14B-Instinct-RP-GGUF: Quantization
- mradermacher/Qwen2.5-14B-Instinct-RP-i1-GGUF: Quantization