model-sft-dare/README.md

base_model, library_name, tags

base_model	library_name	tags
Qwen/Qwen2.5-1.5B-Instruct	transformers	mergekit merge

dare_p1

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear DARE merge method using Qwen/Qwen2.5-1.5B-Instruct as a base.

Models Merged

The following models were included in the merge:

• /kaggle/working/model_sft_lora

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: float16
merge_method: dare_linear
models:
- model: /kaggle/working/model_sft_lora
  parameters:
    density: 0.9
    weight: 1.0
tokenizer_source: base