yuhengtu-bytedance/DataDecide-dolma1_7-no-code-1B-52500_55000_57500_60000_62500_weightedavg_merge
0278
DataDecide-dolma17-no-code-1B-5250055000575006000062500weightedavg_merge
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/sourceckpts/dolma17-no-code/step62500 as a base.
Models Merged
The following models were included in the merge:
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/sourceckpts/dolma17-no-code/step52500
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/sourceckpts/dolma17-no-code/step55000
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/sourceckpts/dolma17-no-code/step60000
- /opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/sourceckpts/dolma17-no-code/step57500
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/dolma1_7-no-code/step52500
parameters:
weight: 1
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dolma1_7-no-code/step55000
parameters:
weight: 2
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dolma1_7-no-code/step57500
parameters:
weight: 3
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dolma1_7-no-code/step60000
parameters:
weight: 4
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dolma1_7-no-code/step62500
parameters:
weight: 5
base_model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/dolma1_7-no-code/step62500
merge_method: linear
parameters:
normalize: true
dtype: float32
out_dtype: bfloat16
