woshilhz001/SenseNova-U1.5-8B-MoT-Q4_0
Full fine-tune vs sensenova/SenseNova-U1.5-8B-MoT. woshilhz001/SenseNova-U1.5-8B-MoT-Q4_0 is a GGUF (Q4_0) of different weights. Fine-tune: 96% of the weights changed, across 42 of 42 layers.
Tensors changed: other 0/4, Embeddings 6/17, lm_head 1/1, Norms 0/506, MLP 252/252, Attention 336/336