model_sft_resta

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 Qwen/Qwen2.5-1.5B-Instruct as a base.

Models Merged

The following models were included in the merge:

outputs/part2/model_harmful_full
outputs/part2/model_sft_full

Configuration

The following YAML configuration was used to produce this model:

models:
- model: Qwen/Qwen2.5-1.5B-Instruct
- model: outputs/part2/model_sft_full
  parameters:
    weight: 1.0
- model: outputs/part2/model_harmful_full
  parameters:
    weight: -1.0
merge_method: task_arithmetic
base_model: Qwen/Qwen2.5-1.5B-Instruct
parameters:
  normalize: false
dtype: bfloat16