marcuscedricridia/etr1o-v1

merge

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 open-r1/OpenR1-Qwen-7B as a base.

Models Merged

The following models were included in the merge:

• Open-Reasoner-Zero/Open-Reasoner-Zero-7B
• open-thoughts/OpenThinker-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: open-r1/OpenR1-Qwen-7B
    #no parameters necessary for base model
  - model: Open-Reasoner-Zero/Open-Reasoner-Zero-7B
    parameters:
      density: 0.5
      weight: 0.5
  - model: open-thoughts/OpenThinker-7B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: della
base_model: open-r1/OpenR1-Qwen-7B
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16