Novaciano/SEX_ROLEPLAY-2B

Full fine-tune vs Novaciano/Hereticsutra-2B. Fine-tune: 100% of the weights changed, across 26 of 26 layers.

Tensors changed: Embeddings 1/1, Norms 105/105, MLP 78/78, Attention 104/104

3 derivatives checked

• mradermacher/SEX_ROLEPLAY-2B-GGUF: Same weights, converted
• mradermacher/SEX_ROLEPLAY-2B-i1-GGUF: Quantization
• Novaciano/SEX_ROLEPLAY-2B-GGUF: Quantization

On the Hub · Downloads on Model Pulse