--- license: other license_name: mistral-ai-research-licence license_link: https://mistral.ai/licenses/MRL-0.1.md base_model: [] library_name: transformers tags: - mergekit - lumikabra-123B --- # lumikabra-123B v0.4
Lumikabra
This is lumikabra. It's based on [Mistral-Large-Instruct-2407 ](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407), merged with Magnum-v2-123B, Luminum-v0.1-123B and Tess-3-Mistral-Large-2-123B. I shamelessly took this idea from [FluffyKaeloky](https://huggingface.co/FluffyKaeloky/Luminum-v0.1-123B). Like him, i always had my troubles with each of the current large mistral based models. Either it gets repetitive, shows too many GPTisms, is too horny or too unhorny. RP and storytelling is always a matter of taste, and i found myself swiping too often for new answers or even fixing them when I missed a little spice or cleverness. Luminum was a great improvement, mixing a lot of desired traits, but I still missed some spice, another sauce. So i took Luminum, added magnum again and also Tess for knowledge and structure. This is the forth iteration. More of the mistral base model. Like all Lumikabra models so far, it tends to write pretty long and creative answers.. ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: /workspace/text-generation-webui/models/anthracite-org_magnum-v2-123b parameters: weight: 0.25 density: 0.9 - model: /workspace/text-generation-webui/models/FluffyKaeloky_Luminum-v0.1-123B parameters: weight: 0.25 density: 0.9 - model: /workspace/text-generation-webui/models/migtissera_Tess-3-Mistral-Large-2-123B parameters: weight: 0.3 density: 0.9 merge_method: della_linear base_model: /workspace/text-generation-webui/models/mistralai_Mistral-Large-Instruct-2407 parameters: epsilon: 0.05 lambda: 1 int8_mask: true dtype: bfloat16 ```