mradermacher/Stentor-30M-Instruct-GGUF
LoRA-style vs StentorLabs/Stentor-30M-Instruct. mradermacher/Stentor-30M-Instruct-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 21 of 21 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/43, MLP 0/63, Attention 42/84