Novaciano/Eminence_Of_Pervertions-3.2-1B
Partial fine-tune vs Novaciano/PHOEBE_SENTIMENTAL-RP-NSFW-3.2-1B. Partial change: 86% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 16 of 16 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 1/33, MLP 38/48, Attention 52/64
3 derivatives checked
- mradermacher/Eminence_Of_Pervertions-3.2-1B-i1-GGUF: Quantization
- mradermacher/Eminence_Of_Pervertions-3.2-1B-GGUF: Same weights, converted
- Novaciano/Hug_Of_Bear-3.2-1B: LoRA-style