metadata
base_model:
- teknium/OpenHermes-2.5-Mistral-7B
- NeverSleep/Noromaid-7B-0.4-DPO
- mistralai/Mistral-7B-v0.1
- Open-Orca/Mistral-7B-OpenOrca
- cognitivecomputations/samantha-1.1-westlake-7b
library_name: transformers
tags:
- mergekit
- merge
Open_Maid_Samantha_Hermes_Orca_dare_tiesv0.1
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using mistralai/Mistral-7B-v0.1 as a base.
Models Merged
The following models were included in the merge:
- teknium/OpenHermes-2.5-Mistral-7B
- NeverSleep/Noromaid-7B-0.4-DPO
- Open-Orca/Mistral-7B-OpenOrca
- cognitivecomputations/samantha-1.1-westlake-7b
Configuration
The following YAML configuration was used to produce this model:
models:
- model: mistralai/Mistral-7B-v0.1
# No parameters necessary for base model
- model: cognitivecomputations/samantha-1.1-westlake-7b
parameters:
density: 0.59
weight: 0.15
- model: NeverSleep/Noromaid-7B-0.4-DPO
parameters:
density: 0.59
weight: 0.3
- model: teknium/OpenHermes-2.5-Mistral-7B
parameters:
density: 0.49
weight: 0.3
- model: Open-Orca/Mistral-7B-OpenOrca
parameters:
density: 0.49
weight: 0.25
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16