ChaoticNeutrals/Captain_Eris_Noctis-12B-v0.420
LoRA-style vs ChaoticNeutrals/Captain-Eris-Diogenes_Twilight-V0.420-12B. 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: lm_head 0/1, Embeddings 0/1, Norms 0/81, MLP 117/120, Attention 156/160
4 derivatives checked
- mradermacher/Captain_Eris_Noctis-12B-v0.420-i1-GGUF: Quantization
- mradermacher/Captain_Eris_Noctis-12B-v0.420-GGUF: Quantization
- EldritchLabs/KrakenSakura-Maelstrom-12B-v1: Full fine-tune
- ewald1976/gas-station-12b-v3: Full fine-tune