igomsmiranda/qwen2.5-7b_instruct-math7b_linear_50_b

merge

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

Merge Details

Benchmarks

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
tinyBenchmarks	N/A
- tinyArc	0	none	25	acc_norm	↑	0.5537	±	N/A
- tinyGSM8k	0	flexible-extract	5	exact_match	↑	0.7686	±	N/A
		strict-match	5	exact_match	↑	0.7421	±	N/A
- tinyHellaswag	0	none	10	acc_norm	↑	0.6475	±	N/A
- tinyMMLU	0	none	0	acc_norm	↑	0.5841	±	N/A
- tinyTruthfulQA	0	none	0	acc	↑	0.5356	±	N/A
- tinyWinogrande	0	none	5	acc_norm	↑	0.6316	±	N/A

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

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

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2.5-7B-Instruct
    parameters:
      weight: 0.5
  - model: Qwen/Qwen2.5-Math-7B-Instruct
    parameters:
      weight: 0.5
merge_method: linear
dtype: bfloat16