Mungert/QED-Nano-GGUF
Full fine-tune vs lm-provers/QED-Nano-SFT. Mungert/QED-Nano-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 132/145, MLP 108/108, Attention 144/144