QuantFactory/Llama-Sentient-3.2-3B-Instruct-GGUF
Full fine-tune vs meta-llama/Llama-3.2-3B-Instruct. QuantFactory/Llama-Sentient-3.2-3B-Instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 112/112