| base_model: | |
| - mistralai/Mistral-7B-Instruct-v0.2 | |
| library_name: transformers | |
| tags: | |
| - mergekit | |
| - merge | |
| # 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 [linear](https://arxiv.org/abs/2203.05482) merge method. | |
| ### Models Merged | |
| The following models were included in the merge: | |
| * [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | |
| ### Configuration | |
| The following YAML configuration was used to produce this model: | |
| ```yaml | |
| dtype: float16 | |
| merge_method: linear | |
| slices: | |
| - sources: | |
| - layer_range: [0, 16] # Assuming the first half of the model is more general and can be reduced more | |
| model: mistralai/Mistral-7B-Instruct-v0.2 | |
| parameters: | |
| weight: 0.5 # Reduce the weight of the first half to make room for the second half | |
| - layer_range: [16, 32] # Assuming the second half of the model is more specialized and can be reduced less | |
| model: mistralai/Mistral-7B-Instruct-v0.2 | |
| parameters: | |
| weight: 0.5 # Maintain the weight of the second half | |
| ``` | |