NexesMess/Llama_3.2_1b_Abliteratest_SCE
Full fine-tune vs Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Norms 33/33, MLP 48/48, Attention 64/64
6 derivatives checked
- Novaciano/SEX_ROLEPLAY-3.2-1B: Full fine-tune
- Novaciano/SEX_ROLEPLAY-3.2-1B-Q4_K_M-GGUF: Full fine-tune
- Novaciano/SEX_ROLEPLAY-3.2-1B-Q6_K-GGUF: Full fine-tune
- Novaciano/SEX_ROLEPLAY-3.2-1B-Q8_0-GGUF: Full fine-tune
- mradermacher/Llama_3.2_1b_Abliteratest_SCE-GGUF: Same weights, converted
- Novaciano/SEX_ROLEPLAY-3.2-1B-IQ4_XS-GGUF: Full fine-tune