metadata
base_model:
- grimjim/mistralai-Mistral-Nemo-Base-2407
- grimjim/mistralai-Mistral-Nemo-Instruct-2407
library_name: transformers
tags:
- mergekit
- merge
license: apache-2.0
pipeline_tag: text-generation
Mistral-Nemo-Instruct-2407-12B-Xmerge-Mk1
This is a novel merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DeLERP merge method using grimjim/mistralai-Mistral-Nemo-Base-2407 as a base.
DeLERP is a novel merge method, a variation on LERP, implemented within the mergekit framework. More details will be released later.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: grimjim/mistralai-Mistral-Nemo-Instruct-2407
- model: grimjim/mistralai-Mistral-Nemo-Base-2407
merge_method: delerp
base_model: grimjim/mistralai-Mistral-Nemo-Base-2407
parameters:
t:
- value: 0.999
dtype: bfloat16