Mungert/DR-Tulu-8B-GGUF
Full fine-tune vs rl-research/DR-Tulu-SFT-8B. Mungert/DR-Tulu-8B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 92% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 90/145, MLP 108/108, Attention 144/144, lm_head 1/1