metadata
base_model:
- mistralai/Mistral-7B-Instruct-v0.2
- KatyTheCutie/LemonadeRP-4.5.3
- rombodawg/Everyone-LLM-7b-Base
- Endevor/InfinityRP-v1-7B
- mistralai/Mistral-7B-v0.1
- argilla/CapybaraHermes-2.5-Mistral-7B
library_name: transformers
tags:
- mergekit
- merge
starfish2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the task arithmetic merge method using mistralai/Mistral-7B-v0.1 as a base.
Models Merged
The following models were included in the merge:
- mistralai/Mistral-7B-Instruct-v0.2
- KatyTheCutie/LemonadeRP-4.5.3
- rombodawg/Everyone-LLM-7b-Base
- Endevor/InfinityRP-v1-7B
- argilla/CapybaraHermes-2.5-Mistral-7B
Configuration
The following YAML configuration was used to produce this model:
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: task_arithmetic
slices:
- sources:
- layer_range: [0, 32]
model: mistralai/Mistral-7B-v0.1
- layer_range: [0, 32]
model: KatyTheCutie/LemonadeRP-4.5.3
parameters:
weight: 0.43
- layer_range: [0, 32]
model: Endevor/InfinityRP-v1-7B
parameters:
weight: 0.40
- layer_range: [0, 32]
model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
weight: 0.20
- layer_range: [0, 32]
model: rombodawg/Everyone-LLM-7b-Base
parameters:
weight: 0.14
- layer_range: [0, 32]
model: argilla/CapybaraHermes-2.5-Mistral-7B
parameters:
weight: 0.18