Felladrin/gguf-Minueza-32M-UltraChat
LoRA-style vs Felladrin/Minueza-32M-UltraChat. Felladrin/gguf-Minueza-32M-UltraChat 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 changed, in 10 of 10 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/21, MLP 0/30, Attention 20/40