QuantFactory/Llama-3.1-Tulu-3-8B-SFT-GGUF
Full fine-tune vs meta-llama/Llama-3.1-8B. QuantFactory/Llama-3.1-Tulu-3-8B-SFT-GGUF is a GGUF (Q8_0) 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