This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Task Arithmetic merge method using
Athkal/model-sft-lora as a base.
1base_model: Athkal/model-sft-lora
2dtype: float16
3merge_method: task_arithmetic
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 28]
9 model: Qwen/Qwen2.5-1.5B-Instruct
10 parameters:
11 weight: 1.0
12 - layer_range: [0, 28]
13 model: /kaggle/working/model_harmful_lora
14 parameters:
15 weight: -1.0
16 - layer_range: [0, 28]
17 model: Athkal/model-sft-lora
18tokenizer_source: base
