Felladrin/gguf-TinyMistral-248M-SFT-v4
Full fine-tune vs Felladrin/TinyMistral-248M-Chat-v4. Felladrin/gguf-TinyMistral-248M-SFT-v4 is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 12 of 12 layers.
Tensors changed: Norms 25/25, MLP 36/36, Attention 48/48