yuhengtu-bytedance/DataDecide-dclm-baseline-qc-10p-1B-0_2500_5000_7500_10000_weightedavg_merge
0648
DataDecide-dclm-baseline-qc-10p-1B-025005000750010000weightedavgmerge
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-10p/step10000 as a base.
Models Merged
The following models were included in the merge:
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-10p/step7500
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-10p/step0
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-10p/step2500
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/dclm-baseline-qc-10p/step5000
Configuration
The following YAML configuration was used to produce this model:
models:
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-10p/step0
parameters:
weight: 1
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-10p/step2500
parameters:
weight: 2
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-10p/step5000
parameters:
weight: 3
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-10p/step7500
parameters:
weight: 4
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-10p/step10000
parameters:
weight: 5
base_model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dclm-baseline-qc-10p/step10000
merge_method: linear
parameters:
normalize: true
dtype: float32
out_dtype: bfloat16
