SzilviaB/DarkNeuralDaredevil-8b-abliterated
Partial fine-tune vs DavidAU/L3-Dark-Planet-8B. Partial change: 81% of the weights changed (attention, mlp, norms), in 30 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 58/65, MLP 90/96, Attention 120/128
3 derivatives checked
- mradermacher/DarkNeuralDaredevil-8b-abliterated-i1-GGUF: Quantization
- mradermacher/DarkNeuralDaredevil-8b-abliterated-GGUF: Same weights, converted
- SzilviaB/SuperDarkUnholyNeuralDaredevil-8b: Full fine-tune