mayacinka/yam-jom-7B-ties
Full fine-tune vs eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2. Fine-tune: 92% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 2/65, MLP 91/96, Attention 123/128, lm_head 0/1
1 derivatives checked
- mradermacher/yam-jom-7B-ties-GGUF: Same weights, converted