Aryanne/Open-StarLake-Swap-7B
Full fine-tune vs NousResearch/Nous-Hermes-2-Mistral-7B-DPO. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/Open-StarLake-Swap-7B-GGUF: Same weights, converted
- Aryanne/MixSwap: Full fine-tune