IggyLux/MN-VelvetCafe-RP-12B

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/Neona-Dan-Slerp-i1-GGUF: Quantization
• mradermacher/MN-VelvetCafe-RP-12B-i1-GGUF: Quantization
• mradermacher/Neona-Dan-Slerp-GGUF: Quantization
• mradermacher/MN-VelvetCafe-RP-12B-GGUF: Quantization

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse