pmahdavi/Olmo-3.1-7B-Math-Code

merged-model

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

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

• allenai/Olmo-3.1-7B-RL-Zero-Math
• allenai/Olmo-3.1-7B-RL-Zero-Code

Configuration

The following YAML configuration was used to produce this model:

# Linear merge of OLMo-3.1 Math and Code RL models
# Output = 0.5 * Math + 0.5 * Code
#
# Usage:
#   modal run modal_merge.py --config examples/olmo3.1-linear-merge.yaml --hf-repo pmahdavi/Olmo-3.1-7B-Math-Code

models:
  - model: allenai/Olmo-3.1-7B-RL-Zero-Math
    parameters:
      weight: 0.5
  - model: allenai/Olmo-3.1-7B-RL-Zero-Code
    parameters:
      weight: 0.5

merge_method: linear
dtype: bfloat16