mradermacher/KAT-Dev-GGUF
Full fine-tune vs Kwaipilot/KAT-Dev. mradermacher/KAT-Dev-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, Norms 244/257, MLP 192/192, Attention 256/256, lm_head 1/1