nthehai01/Qwen2.5-7B-Instruct-Math-Code-task-arithmetic

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

Performance

Metric	Value
GSM8k (zero-shot)	86.20
HellaSwag (zero-Shot)	49.91
MBPP (zero-shot)	55.20

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-Coder-7B
• 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: 0.5676097213578511
  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: 0.5215841338521604
  - layer_range: [0, 28]
    model: Qwen/Qwen2.5-Coder-7B
    parameters:
      weight: 0.13680114132969845
  - layer_range: [0, 28]
    model: Qwen/Qwen2.5-7B-Instruct
    parameters:
      weight: 0.8507353075455186