mergekit-community/NSFW-FFS-w-hidden-Deepseek-Distill-NSFW-Redux
Full fine-tune vs mergekit-community/Deepseek-R1-Distill-NSFW-RP-vRedux. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128
3 derivatives checked
- mradermacher/NSFW-FFS-w-hidden-Deepseek-Distill-NSFW-Redux-i1-GGUF: Quantization
- mradermacher/NSFW-FFS-w-hidden-Deepseek-Distill-NSFW-Redux-GGUF: Same weights, converted
- mergekit-community/Deepseek-R1-Distill-NSFW-RP-vRedux-Proper: Full fine-tune