mradermacher/DeciLM-7B-instruct-GGUF
LoRA-style vs Deci/DeciLM-7B-instruct. mradermacher/DeciLM-7B-instruct-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 changed, in 11 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 11/128, lm_head 0/1