metadata
base_model:
- prithivMLmods/Llama-Deepsync-3B
- huihui-ai/Llama-3.2-3B-Instruct-abliterated
library_name: transformers
tags:
- mergekit
- merge
license: llama3.2
language:
- en
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Attempt at creating a model that can complete text generation tasks that require deep reasoning, logical structuring, and problem-solving.
But with some censorship removed.
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: prithivMLmods/Llama-Deepsync-3B
- model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
merge_method: slerp
base_model: prithivMLmods/Llama-Deepsync-3B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0]