| base_model: | |
| - mistralai/Mistral-7B-v0.1 | |
| - PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed | |
| - codellama/CodeLlama-7b-Instruct-hf | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| # output_folder merge | |
| This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). | |
| ## Merge Details | |
| ### Merge Method | |
| This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed](https://huggingface.co/PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed) | |
| * [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| models: | |
| - model: mistralai/Mistral-7B-v0.1 # no parameters necessary for base model | |
| - model: PrunaAI/WizardLM-WizardMath-7B-V1.0-bnb-4bit-smashed | |
| parameters: | |
| density: 0.5 # fraction of weights in differences from the base model to retain | |
| weight: # weight gradient | |
| - filter: mlp | |
| value: 0.5 | |
| - value: 0 | |
| - model: codellama/CodeLlama-7b-Instruct-hf | |
| parameters: | |
| density: 0.5 | |
| weight: 0.5 | |
| merge_method: ties | |
| base_model: mistralai/Mistral-7B-v0.1 | |
| parameters: | |
| normalize: true | |
| int8_mask: true | |
| dtype: float16 | |
| ``` | |