mradermacher/Marcoro14-7B-slerp_v2-GGUF
LoRA-style vs oz1115/Marcoro14-7B-slerp_v2. mradermacher/Marcoro14-7B-slerp_v2-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 23 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 42/128