QuantFactory/FastLlama-3.2-1B-Instruct-GGUF
Full fine-tune vs meta-llama/Llama-3.2-1B-Instruct. QuantFactory/FastLlama-3.2-1B-Instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 0/33, MLP 48/48, Attention 64/64