theprint/DoItYourself-v1-2B-GGUF
LoRA-style vs theprint/DoItYourself-v1-2B. theprint/DoItYourself-v1-2B-GGUF is a GGUF (BF16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, up_proj changed, in 13 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 13/72, Attention 2/24