ReadyArt/Omega-Darker_The-Final-Directive-12B
LoRA-style vs mistralai/Mistral-Nemo-Instruct-2407. 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 120/120, Attention 160/160, lm_head 0/1
11 derivatives checked
- mradermacher/Omega-Darker_The-Final-Directive-12B-i1-GGUF: Quantization
- mradermacher/Omega-Darker_The-Final-Directive-12B-GGUF: Quantization
- Vortex5/Maroon-Sunset-12B: Full fine-tune
- pot99rta/DarkThink-DirectiveReasoner-12B: Full fine-tune
- Vortex5/Dark-Quill-12B: Full fine-tune
- pot99rta/NS-12b-DarkSluchCapV3: Full fine-tune
- mergekit-community/mergekit-model_stock-qtseiad: Full fine-tune
- SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2: LoRA-style
- mergekit-community/Omega-Darker_Slush-12B: Partial fine-tune
- pot99rta/OmegaPatricide-12B-DarkerDirective-Mell: Full fine-tune
- Sorihon/Omega-Darker_The-Final-Directive-12B-Heretic: Abliterated