suayptalha/Luminis-phi-4
LoRA-style vs bunnycore/Phi-4-Model-Stock-v4. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 117/120, Attention 156/160
2 derivatives checked
- mradermacher/Luminis-phi-4-i1-GGUF: Quantization
- mradermacher/Luminis-phi-4-GGUF: Quantization