ertghiu256/qwen3-1.7b-mix-ed-tunes-test

merged

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

Merge Details

Merge Method

This model was merged using the DELLA merge method using ertghiu256/qwen3-1.7b-hermes-3-no-thinking as a base.

Models Merged

The following models were included in the merge:

• ertghiu256/qwen3-1.7b-mixture-of-thought
• ertghiu256/Qwen-3-1.7b-deepseek-r1-0528-distillation

Configuration

The following YAML configuration was used to produce this model:

base_model: ertghiu256/qwen3-1.7b-hermes-3-no-thinking
dtype: float16
merge_method: della
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 28]
        model: ertghiu256/qwen3-1.7b-hermes-3-no-thinking
        parameters:
          weight: 0.6
      - layer_range: [0, 28]
        model: ertghiu256/qwen3-1.7b-mixture-of-thought
        parameters:
          weight: 0.7
      - layer_range: [0, 28]
        model: ertghiu256/Qwen-3-1.7b-deepseek-r1-0528-distillation
        parameters:
          weight: 0.8
parameters:
  int8_mask: 1.0
  normalize: 1.0