win10/Norns-Qwen2.5-7B

donate: https://ko-fi.com/ogodwin10

mmlu-pro

overall	biology	business	chemistry	computer science	economics	engineering	health	history	law	math	philosophy	physics	psychology	other
41.46	64.16	45.37	32.51	47.07	52.13	28.79	37.04	37.01	21.98	56.11	34.07	38.03	54.26	37.77

merge

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

Merge Details

Merge Method

This model was merged using the breadcrumbs_ties merge method using win10/Skuld-Qwen2.5-7B as a base.

Models Merged

The following models were included in the merge:

• win10/Urdandi-Qwen2.5-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: win10/Urdandi-Qwen2.5-7B
    parameters:
      density: 1
      weight: 1 
      
  - model: win10/Skuld-Qwen2.5-7B
    parameters:
      density: 1
      weight: 1 
      
  - model: win10/Urdandi-Qwen2.5-7B
    parameters:
      density: 1
      weight: 1 
      
  - model: win10/Skuld-Qwen2.5-7B
    parameters:
      density: 1
      weight: 1 
      
merge_method: breadcrumbs_ties
base_model: win10/Skuld-Qwen2.5-7B
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16