BrainboxAI/cyber-analyst-4B-verifier-pilot
LoRA-style vs BrainboxAI/cyber-analyst-4B. BrainboxAI/cyber-analyst-4B-verifier-pilot is a GGUF (Q4_K_M) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of attn_k, attn_output, attn_q, attn_v, ffn_down, ffn_gate, ffn_up changed, in 0 of 0 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/296, other 0/130, Attention 132/168, MLP 125/126