LiteLLMs/Smaug-72B-v0.1-GGUF
Full fine-tune vs moreh/MoMo-72B-lora-1.8.7-DPO. LiteLLMs/Smaug-72B-v0.1-GGUF is a GGUF (Q8_0/F32) of different weights. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 0/161, MLP 240/240, Attention 320/640, lm_head 1/1