QuantFactory/gemma-2b-aps-it-GGUF
Full fine-tune vs google/gemma-2b. QuantFactory/gemma-2b-aps-it-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 18 of 18 layers.
Tensors changed: Embeddings 1/1, Norms 37/37, MLP 54/54, Attention 72/72