metadata

base_model:
  - mistralai/Mistral-Nemo-Instruct-2407
  - NeverSleep/Lumimaid-v0.2-12B
  - Undi95/LocalC-12B-e2.0
  - intervitens/mini-magnum-12b-v1.1
library_name: transformers
tags:
  - mergekit
  - merge

QuantFactory/Lumimaid-Magnum-12B-GGUF

This is quantized version of Undi95/Lumimaid-Magnum-12B created using llama.cpp

Original Model Card

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>