metadata
base_model:
- berkeley-nest/Starling-LM-7B-alpha
- NousResearch/Nous-Hermes-2-Mistral-7B-DPO
- senseable/WestLake-7B-v2
- openchat/openchat-3.5-0106
library_name: transformers
tags:
- mergekit
- merge
merged
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the task_swapping merge method using senseable/WestLake-7B-v2 as a base.
Models Merged
The following models were included in the merge:
- berkeley-nest/Starling-LM-7B-alpha
- NousResearch/Nous-Hermes-2-Mistral-7B-DPO
- openchat/openchat-3.5-0106
Configuration
The following YAML configuration was used to produce this model:
base_model:
model:
path: senseable/WestLake-7B-v2
dtype: bfloat16
merge_method: task_swapping
slices:
- sources:
- layer_range: [0, 32]
model:
model:
path: berkeley-nest/Starling-LM-7B-alpha
parameters:
diagonal_offset: 2.0
weight: 0.72
- layer_range: [0, 32]
model:
model:
path: openchat/openchat-3.5-0106
parameters:
diagonal_offset: 4.0
random_mask: 0.166
random_mask_seed: 19519.0
weight: 0.4
- layer_range: [0, 32]
model:
model:
path: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
parameters:
diagonal_offset: 4.0
random_mask: 0.125
random_mask_seed: 990090.0
weight: 0.666
- layer_range: [0, 32]
model:
model:
path: senseable/WestLake-7B-v2