pmahdavi/Olmo-3-7B-Think-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 Task Arithmetic merge method using allenai/Olmo-3-1025-7B as a base.

Models Merged

The following models were included in the merge:

• allenai/Olmo-3-7B-RL-Zero-Math
• allenai/Olmo-3-7B-RL-Zero-Code
• allenai/Olmo-3-7B-Think-SFT

Configuration

The following YAML configuration was used to produce this model:

# Task arithmetic merge: Apply Math+Code task vectors to Think-SFT
#
# Mathematical formulation:
#   output = Think-SFT + 0.5*(RL-Zero-Math - base) + 0.5*(RL-Zero-Code - base)
#
# This is achieved by treating Think-SFT as a model with weight=1.0:
#   output = base + 1.0*(Think-SFT - base) + 0.5*(Math - base) + 0.5*(Code - base)
#
# Usage:
#   modal run modal_merge.py --config examples/olmo-think-math-code.yaml --hf-repo pmahdavi/Olmo-3-7B-Think-Math-Code

merge_method: task_arithmetic
base_model: allenai/Olmo-3-1025-7B
models:
  - model: allenai/Olmo-3-7B-Think-SFT
    parameters:
      weight: 1.0
  - model: allenai/Olmo-3-7B-RL-Zero-Math
    parameters:
      weight: 0.5
  - model: allenai/Olmo-3-7B-RL-Zero-Code
    parameters:
      weight: 0.5
dtype: bfloat16