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 allknowingroger/QwenSlerp6-14B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: CultriX/Qwen2.5-14B-Wernicke
- model: sometimesanotion/Qwen2.5-14B-Vimarckoso
- model: sometimesanotion/lamarck-14b-prose-model_stock
- model: sometimesanotion/lamarck-14b-prose-model_stock
- model: allknowingroger/QwenSlerp6-14B
merge_method: model_stock
base_model: allknowingroger/QwenSlerp6-14B
normalize: false
int8_mask: true
dtype: bfloat16