Mungert/Spark-X2.5-1.7B-GGUF
Full fine-tune vs XHToken/Spark-X2.5-1.7B-Base. Mungert/Spark-X2.5-1.7B-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 57/57, MLP 84/84, Attention 56/56