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 mergekit-community/Qwen2-2B-RepleteCoder-Upscaled as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: mergekit-community/Qwen2-2B-RepleteCoder-Hercules
- model: mergekit-community/Qwen2-2B-Dolphin-Hercules
- model: mergekit-community/Qwen2-2B-Dolphin-RepleteCoder
- model: mergekit-community/Qwen2-Math-2B-Instruct
merge_method: model_stock
base_model: mergekit-community/Qwen2-2B-RepleteCoder-Upscaled
architecture: qwen2
dtype: bfloat16