ArRENCEAI/Phi-4-Mini-Instruct-Obliterated-zero

Partial fine-tune vs microsoft/Phi-4-mini-instruct. Partial change: 55% of the weights changed (attention, embeddings, mlp), in 30 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 0/65, MLP 30/64, Attention 60/64

2 derivatives checked

• mradermacher/Phi-4-Mini-Instruct-Obliterated-zero-i1-GGUF: Quantization
• mradermacher/Phi-4-Mini-Instruct-Obliterated-zero-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse