mradermacher/dragon-mistral-7b-v0-i1-GGUF
LoRA-style vs llmware/dragon-mistral-7b-v0. mradermacher/dragon-mistral-7b-v0-i1-GGUF is a GGUF (Q6_K) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of attn_v, ffn_down changed, in 0 of 0 layers; norms, biases and embeddings are untouched.
Tensors changed: other 0/1, Attention 16/128, MLP 16/96, Norms 0/65, lm_head 0/1