Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using yamatazen/EtherealAurora-12B + nbeerbower/Mistral-Nemo-12B-abliterated-LORA as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: yamatazen/EtherealAurora-12B+nbeerbower/Mistral-Nemo-12B-abliterated-LORA
models:
- model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
- model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
- model: TheDrummer/Rocinante-12B-v1.1
merge_method: model_stock
dtype: bfloat16
parameters:
normalize: true