Novaciano/HarmfulProject-3.2-1B
Full fine-tune vs Grogros/Grogros-dmWM-LLama-3-1B-Harm-HarmData-Al4-OWT-d4-a0.25-learnability_adv. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64
2 derivatives checked
- mradermacher/UNCENSORED-HarmfulProject-3.2-1B-i1-GGUF: Quantization
- mradermacher/UNCENSORED-HarmfulProject-3.2-1B-GGUF: Same weights, converted