bunnycore/Phi-3.5-mini-TitanFusion-0.1
LoRA-style vs ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_up_proj, o_proj, qkv_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 62/64, Attention 60/64, lm_head 0/1
2 derivatives checked
- mradermacher/Phi-3.5-mini-TitanFusion-0.1-i1-GGUF: Quantization
- mradermacher/Phi-3.5-mini-TitanFusion-0.1-GGUF: Same weights, converted