mradermacher/tinyllama-15M-alpaca-finetuned-GGUF
LoRA-style vs elvinmarkmv/tinyllama-15M-alpaca-finetuned. mradermacher/tinyllama-15M-alpaca-finetuned-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 changed, in 6 of 6 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/13, MLP 0/18, Attention 12/24