MarsupialAI/Llama-3.1-Nemotron-70B-Instruct_iMat_GGUF
Full fine-tune vs meta-llama/Llama-3.1-70B-Instruct. MarsupialAI/Llama-3.1-Nemotron-70B-Instruct_iMat_GGUF is a GGUF (FP16) of different weights. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 88/161, MLP 240/240, Attention 320/320, lm_head 1/1