Modelpublic

yuhengtu-bytedance/DataDecide-dclm-baseline-qc-7p-fw2-1B-22500_25000_27500_30000_32500_weightedavg_merge

sourceHugging Faceupdated 13d agoView on Hugging Face

0likes68downloads

Model Card

DataDecide-dclm-baseline-qc-7p-fw2-1B-2250025000275003000032500weightedavgmerge

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 using /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-7p-fw2/step32500 as a base.

Models Merged

The following models were included in the merge:

—/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-7p-fw2/step27500
—/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-7p-fw2/step30000
—/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-7p-fw2/step25000
—/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-7p-fw2/step22500

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-7p-fw2/step22500
  parameters:
    weight: 1
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-7p-fw2/step25000
  parameters:
    weight: 2
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-7p-fw2/step27500
  parameters:
    weight: 3
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-7p-fw2/step30000
  parameters:
    weight: 4
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-7p-fw2/step32500
  parameters:
    weight: 5
base_model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-7p-fw2/step32500
merge_method: linear
parameters:
  normalize: true
dtype: float32
out_dtype: bfloat16