Kukedlc/NeuTrixOmniBe-7B-model-remix
Full fine-tune vs CultriX/NeuralTrix-7B-dpo. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
5 derivatives checked
- jsfs11/MixtureofMerges-MoE-4x7b-v4: MoE built from dense models
- eren23/merged-dpo-binarized-NeutrixOmnibe-7B: Full fine-tune
- jsfs11/MoEv4Config-TestWeightedTIES-7b: Full fine-tune
- paulml/NMTOB-7B: Full fine-tune
- jsfs11/MoEv4Config-TIESwithRescale-7b: Full fine-tune