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 Aleteian/Saiga-Unleashed as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Aleteian/Neverending-Story-MN-12B
- model: Aleteian/Instrumentality-2-MN-12B-RP
- model: Aleteian/Pathfinder-RP-12B-RU
- model: Aleteian/On-the-Strange-Lands-MN-12B
- model: Aleteian/Way-to-Unseen-Horizon-MN-12B
- model: Aleteian/Omnino-Obscoenum-Opus-Magnum-MN-12B
- model: Aleteian/Magnum-Opus-Galatea-MN-12B
- model: Aleteian/Follow-the-Flow-MN-12B
merge_method: model_stock
base_model: Aleteian/Saiga-Unleashed
dtype: bfloat16
tokenizer_source: "union"
chat_template: "mistral"