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 OpenBuddy/openbuddy-mistral2-7b-v20.3-32k as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Gaivoronsky/Mistral-7B-Saiga
- model: OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
- model: meta-math/MetaMath-Mistral-7B
- model: HuggingFaceH4/mistral-7b-anthropic
- model: NousResearch/Yarn-Mistral-7b-128k
- model: ajibawa-2023/Code-Mistral-7B
merge_method: model_stock
base_model: OpenBuddy/openbuddy-mistral2-7b-v20.3-32k
dtype: bfloat16