OmnicromsBrain/NeuralStar_AlphaWriter_4x7b
MoE built from dense models vs FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B. OmnicromsBrain/NeuralStar_AlphaWriter_4x7b is a mixture of 4 experts assembled from dense models (mergekit-moe style): expert 1 is an exact copy of FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B's MLP; the other experts come from other models. Shared tensors (attention, norms, embeddings): 0 of 193 identical.
2 derivatives checked
- mradermacher/NeuralStar_AlphaWriter_4x7b-i1-GGUF: Quantization
- mradermacher/NeuralStar_AlphaWriter_4x7b-GGUF: Quantization