Azazelle/Llama-3-8B-contaminated-roleplay
Full fine-tune vs ResplendentAI/Aura_Uncensored_l3_8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 16/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- mradermacher/Llama-3-8B-contaminated-roleplay-i1-GGUF: Quantization
- mradermacher/Llama-3-8B-contaminated-roleplay-GGUF: Same weights, converted
- mergekit-community/Llama-3-ThinkRoleplay-DeepSeek-R1-Distill-8B-abliterated: Full fine-tune
- Azazelle/Llama-3-8B-Help-Me: Full fine-tune