Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
Stella-Neural-Abliterated-Mahou-Devil
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using nbeerbower/llama-3-Stheno-Mahou-8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: mlabonne/NeuralDaredevil-8B-abliterated
- model: nbeerbower/llama-3-spicy-abliterated-stella-8B
- model: nbeerbower/llama-3-Daredevil-Mahou-8B
merge_method: model_stock
base_model: nbeerbower/llama-3-Stheno-Mahou-8B
dtype: bfloat16
3-bit
4-bit
5-bit