Nitral-Archive/Nera_Noctis-12B-v0.420
LoRA-style vs ChaoticNeutrals/Nera_Noctis-12B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 117/120, Attention 156/160, lm_head 0/1
2 derivatives checked
- mradermacher/Nera_Noctis-12B-v0.420-i1-GGUF: Quantization
- mradermacher/Nera_Noctis-12B-v0.420-GGUF: Quantization