mradermacher/RoGemma-7b-Instruct-GGUF
Full fine-tune vs OpenLLM-Ro/RoGemma-7b-Instruct. mradermacher/RoGemma-7b-Instruct-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 16/57, MLP 84/84, Attention 112/112