knifeayumu/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP
Full fine-tune vs TheDrummer/Rocinante-12B-v1. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 30/81, MLP 117/120, Attention 156/160, lm_head 1/1
4 derivatives checked
- mradermacher/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-i1-GGUF: Quantization
- knifeayumu/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-GGUF: Same weights, converted
- mradermacher/Rocinante-12B-v1-nemo-sunfall-v0.6.1-SLERP-GGUF: Quantization
- mergekit-community/Slush-ChatWaifu-Rocinante-sunfall: Full fine-tune