IggyLux/MN-VelvetCafe-RP-12B-V2
Full fine-tune vs PocketDoc/Dans-PersonalityEngine-V1.3.0-12b. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/MN-VelvetCafe-RP-12B-V2-i1-GGUF: Quantization
- mradermacher/MN-VelvetCafe-RP-12B-V2-GGUF: Quantization
- EldritchLabs/MN-Starlight-Sylph-12B: Full fine-tune
- EldritchLabs/MN-Crimson-Cafe-12B: Full fine-tune
1 other repos hold byte-for-byte identical weight files.