bunnycore/Phi-4-RP-v0
Partial fine-tune vs Undi95/Phi4-abliterated. Partial change: 37% of the weights changed (attention, mlp, norms), in 40 of 40 layers.
Tensors changed: Embeddings 0/1, Norms 78/81, MLP 43/80, Attention 45/80, lm_head 0/1
2 derivatives checked
- mradermacher/Phi-4-RP-v0-i1-GGUF: Quantization
- mradermacher/Phi-4-RP-v0-GGUF: Quantization