mradermacher/Mistral-v0.1-Italian-SAVA-instruct-GGUF
Full fine-tune vs SemanticAlignment/Mistral-v0.1-Italian-SAVA-instruct. mradermacher/Mistral-v0.1-Italian-SAVA-instruct-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128