QuantFactory/ghost-8b-beta-1608-GGUF
Full fine-tune vs ghost-x/ghost-8b-beta. QuantFactory/ghost-8b-beta-1608-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1