Qwen2.5-7B-Instruct-Math-task-arithmetic

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

Performance

Metric	Value
GSM8k (zero-shot)	91.35
HellaSwag (zero-Shot)	80.01
MBPP (zero-shot)	61.01

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using Qwen/Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-Math-7B
• Qwen/Qwen2.5-7B-Instruct

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-7B
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  lambda: 0.7870041304118442
  normalize: 1.0
slices:
- sources:
  - layer_range: [0, 28]
    model: Qwen/Qwen2.5-7B
  - layer_range: [0, 28]
    model: Qwen/Qwen2.5-Math-7B
    parameters:
      weight: 0.11841208483160265
  - layer_range: [0, 28]
    model: Qwen/Qwen2.5-7B-Instruct
    parameters:
      weight: 0.7783861791140264