Mungert/NVIDIA-Nemotron-Nano-12B-v2-GGUF
Full fine-tune vs nvidia/NVIDIA-Nemotron-Nano-12B-v2-Base. Mungert/NVIDIA-Nemotron-Nano-12B-v2-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 1/1, Norms 63/63, lm_head 1/1