SuperbEmphasis/The-Omega-Directive-12B-EVISCERATED-FT
LoRA-style vs SuperbEmphasis/The-Omega-Directive-12B-EVISCERATED. 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 34 of 34 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 102/102, Attention 136/136
2 derivatives checked
- mradermacher/The-Omega-Directive-12B-EVISCERATED-FT-i1-GGUF: Quantization
- mradermacher/The-Omega-Directive-12B-EVISCERATED-FT-GGUF: Same weights, converted