mradermacher/Delphi-7B-v1-GGUF
LoRA-style vs thaddickson/Delphi-7B-v1. mradermacher/Delphi-7B-v1-GGUF is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 112/196