metadata
base_model:
- mergekit-community/mergekit-model_stock-ysywggg
- surya-narayanan/professional_psychology
- mergekit-community/nsfw_merge_test_v4dot1
- surya-narayanan/formal_logic
- mergekit-community/mergekit-model_stock-rxbbxes
- kik41/lora-length-long-llama-3-8b-v2
- mergekit-community/NSFW-FFS-w-hidden-Deepseek-Distill-NSFW
- mergekit-community/mergekit-model_stock-fpfjlqs
- Azazelle/ANJIR-ADAPTER-128
library_name: transformers
tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SCE merge method using mergekit-community/NSFW-FFS-w-hidden-Deepseek-Distill-NSFW as a base.
Models Merged
The following models were included in the merge:
- mergekit-community/mergekit-model_stock-ysywggg + surya-narayanan/professional_psychology
- mergekit-community/nsfw_merge_test_v4dot1 + surya-narayanan/formal_logic
- mergekit-community/mergekit-model_stock-rxbbxes + kik41/lora-length-long-llama-3-8b-v2
- mergekit-community/mergekit-model_stock-fpfjlqs + Azazelle/ANJIR-ADAPTER-128
Configuration
The following YAML configuration was used to produce this model:
models:
- model: mergekit-community/nsfw_merge_test_v4dot1+surya-narayanan/formal_logic
- model: mergekit-community/mergekit-model_stock-ysywggg+surya-narayanan/professional_psychology
- model: mergekit-community/mergekit-model_stock-rxbbxes+kik41/lora-length-long-llama-3-8b-v2
- model: mergekit-community/mergekit-model_stock-fpfjlqs+Azazelle/ANJIR-ADAPTER-128
merge_method: sce
base_model: mergekit-community/NSFW-FFS-w-hidden-Deepseek-Distill-NSFW
parameters:
select_topk: 1.0
dtype: bfloat16