Xiaojian9992024/Singularity-Qwen2.5-1.5B

merge

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

Merge Details

Merge Method

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

Models Merged

The following models were included in the merge:

• SakanaAI/TinySwallow-1.5B-Instruct
• bond005/meno-tiny-0.1
• rubenroy/Zurich-1.5B-GCv2-5m
• cutelemonlili/Qwen2.5-1.5B-Instruct_MATH_training_response_Qwen2.5_72B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-1.5B-Instruct
    #no parameters necessary for base model
  - model: bond005/meno-tiny-0.1
    parameters:
      density: 0.25
      weight: 0.25
  - model: SakanaAI/TinySwallow-1.5B-Instruct
    parameters:
      density: 0.25
      weight: 0.25
  - model: rubenroy/Zurich-1.5B-GCv2-5m
    parameters:
      density: 0.25
      weight: 0.25
  - model: cutelemonlili/Qwen2.5-1.5B-Instruct_MATH_training_response_Qwen2.5_72B
    parameters:
      density: 0.25
      weight: 0.25
merge_method: ties
base_model: Qwen/Qwen2.5-1.5B-Instruct
parameters:
  normalize: false
  int8_mask: true
dtype: float16