Mungert/Arch-Router-1.5B-GGUF
Partial fine-tune vs Qwen/Qwen2.5-1.5B-Instruct. Mungert/Arch-Router-1.5B-GGUF is a GGUF (Q8_0) of different weights. Partial change: 85% of the weights changed (attention, mlp, norms), in 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 43/57, MLP 84/84, Attention 195/196