austral-grpo-merged-r1

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

Merge Details

Merge Method

This model was merged using the Passthrough merge method using Delta-Vector/MS3.2-Austral-Winton + /home/dgxuser/workspace/Mango/verifiers/outputs/writing-judge-training-1e-5-power-2/checkpoint-40 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: Delta-Vector/MS3.2-Austral-Winton+/home/dgxuser/workspace/Mango/verifiers/outputs/writing-judge-training-1e-5-power-2/checkpoint-40
dtype: bfloat16
merge_method: passthrough
models:
  - model: Delta-Vector/MS3.2-Austral-Winton+/home/dgxuser/workspace/Mango/verifiers/outputs/writing-judge-training-1e-5-power-2/checkpoint-40