wigcheng5566/laya-neutron-gguf
Partial fine-tune (fewer layers) vs convaiinnovations/laya. wigcheng5566/laya-neutron-gguf matches part of convaiinnovations/laya (35 of its 206 tensors; the rest of convaiinnovations/laya has no counterpart). On the shared part: wigcheng5566/laya-neutron-gguf is a GGUF (F16) of different weights. Partial change: 83% of the weights changed (attention, norms, other), in 2 of 2 layers.
Tensors changed: other 14/19, Norms 8/8, Attention 8/8