base_model, library_name, tags

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

dare_p0.5

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:

• outputs/model_sft_lora

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-1.5B-Instruct
    parameters:
      density: 1.0
      weight: 1.0
  - model: outputs/model_sft_lora
    parameters:
      density: 0.50
      weight: 1.0
merge_method: dare_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
dtype: bfloat16