metadata
base_model:
- v000000/Qwen2.5-Lumen-14B
- huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
library_name: transformers
tags:
- mergekit
- merge
- qwen2
license: apache-2.0
Deepseek-Lumen-R1 (DISTILLED)
Better generalized & instruct following (IFEVAL) deepseek test
Seems improved
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Linear DELLA merge method using huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
parameters:
weight: 1.0
density: 0.9
- model: v000000/Qwen2.5-Lumen-14B
parameters:
weight: 0.25
density: 0.88
merge_method: della_linear
base_model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
parameters:
int8_mask: true
epsilon: 0.07
lambda: 1
dtype: bfloat16