Arx12/Maple-Preview-Exact-GGUF
LoRA-style vs deepgrove/maple-preview. Arx12/Maple-Preview-Exact-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 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Norms 0/97, MLP 0/24, Attention 96/96, Embeddings 0/1