mradermacher/MFANN-liminerity-slerp-4a-GGUF
LoRA-style vs netcat420/MFANN-liminerity-slerp-4a. mradermacher/MFANN-liminerity-slerp-4a-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, q_proj, v_proj changed, in 31 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/2, Embeddings 0/1, Norms 0/66, MLP 0/128, Attention 93/256