mradermacher/Xor-26B-A4B-GGUF
Full fine-tune vs juspay/Xor-26B-A4B. mradermacher/Xor-26B-A4B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 0/271, MLP 90/90, other 29/30, Attention 115/115