matrixportalx/Einstein-v8-Llama3.2-1B-GGUF
Full fine-tune vs meta-llama/Llama-3.2-1B. matrixportalx/Einstein-v8-Llama3.2-1B-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Norms 30/33, MLP 48/48, Attention 64/64