TheBloke/laser-dolphin-mixtral-2x7b-dpo-GGUF
Full fine-tune vs macadeliccc/laser-dolphin-mixtral-2x7b-dpo. TheBloke/laser-dolphin-mixtral-2x7b-dpo-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, other 32/32, Attention 128/128