eren23/merged-dpo-binarized-NeutrixOmnibe-7B
Full fine-tune vs Kukedlc/NeuTrixOmniBe-7B-model-remix. Fine-tune: 91% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 93/96, Norms 3/65, Attention 111/128, lm_head 0/1, Embeddings 0/1
3 derivatives checked
- mradermacher/merged-dpo-binarized-NeutrixOmnibe-7B-i1-GGUF: Quantization
- mradermacher/merged-dpo-binarized-NeutrixOmnibe-7B-GGUF: Quantization
- paulml/DPOB-INMTOB-7B: Full fine-tune