FiShota/yamato-3b-v1-legal-gguf
LoRA-style vs sbintuitions/sarashina2.2-3b-instruct-v0.1. FiShota/yamato-3b-v1-legal-gguf is a GGUF (FP16) 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 128/128