DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF
LoRA-style vs DuoNeural/LFM2.5-8B-A1B-Abliterated. DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF is a GGUF (BF16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, out_proj, q_proj, v_proj, w1, w2, w3 changed, in 8 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, other 0/36, MLP 6/28, Norms 0/60, Attention 24/24