Merge of Lumimaid and Magnum as requested by some.

I used the new DELLA merge method in mergekit and added a finetune of Nemo only on Claude input, trained on 16k ctx, in the mix.

Prompt template: Mistral

<s>[INST] {input} [/INST] {output}</s>

GGUF

Model size

12.2B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Undi95/Lumimaid-Magnum-12B-GGUF

Merge model

this model