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 marcuscedricridia/Springer-32B-Restore as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: model_stock
base_model: marcuscedricridia/Springer-32B-Restore
models:
- model: marcuscedricridia/Springer1.1-32B-Qwen2.5-Reasoning
- model: marcuscedricridia/Springer1.1-32B-Qwen2.5-Coder
- model: marcuscedricridia/Springer1.1-32B-Qwen2.5-Extras
- model: marcuscedricridia/Springer1.1-32B-Qwen2.5-RP
dtype: bfloat16
tokenizer_source: base
int8_mask: true
normalize: true
name: Springer1.1-32B-Qwen2.5-Super