mradermacher/ERNIE-4.5-21B-A3B-Base-PT-GGUF
Full fine-tune vs baidu/ERNIE-4.5-21B-A3B-Base-PT. mradermacher/ERNIE-4.5-21B-A3B-Base-PT-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: MLP 111/111, Embeddings 1/1, Norms 0/57, Attention 112/112