DazzlingXeno/GutenBerg_Nyxora
LoRA-style vs SteelStorage/G2-DA-Nyxora-27b-V2. 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 46 of 46 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/185, MLP 135/138, Attention 180/184
3 derivatives checked
- mradermacher/GutenBerg_Nyxora-i1-GGUF: Quantization
- mradermacher/GutenBerg_Nyxora-GGUF: Quantization
- mergekit-community/GutenBerg_Nyxora_magnum-v4-27b: Full fine-tune