amylynn/Riverfish-Rocinante-12B
Full fine-tune vs TheDrummer/Rivermind-Lux-12B-v1. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 41/81, MLP 120/120, Attention 160/160, lm_head 1/1
3 derivatives checked
- mradermacher/Riverfish-Rocinante-12B-i1-GGUF: Quantization
- mradermacher/Riverfish-Rocinante-12B-GGUF: Quantization
- amylynn/Riverfish-Rocinante-12B-SFT: LoRA-style