Novaciano/Perverted_Literature-3.2-1B
Full fine-tune vs Novaciano/Novaciano-The_Pervert-NSFW-RP-3.2-1B. Fine-tune: 90% of the weights changed, across 16 of 16 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 32/33, MLP 41/48, Attention 55/64
3 derivatives checked
- FelixFester/Perverted_Literature-3.2-1B-i1-GGUF: Quantization
- mradermacher/Perverted_Literature-3.2-1B-i1-GGUF: Quantization
- Novaciano/Aspid-3.2-1B: Partial fine-tune
1 other repos hold byte-for-byte identical weight files.