CoolFace
Modelpublic

yuhengtu-bytedance/DataDecide-falcon-and-cc-qc-orig-10p-1B-57500_60000_62500_65000_67500_weightedavg_merge

sourceHugging Faceupdated 10d agoView on Hugging Face
0likes253downloads
Model Card

DataDecide-falcon-and-cc-qc-orig-10p-1B-5750060000625006500067500weightedavgmerge

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/falcon-and-cc-qc-orig-10p/step67500 as a base.

Models Merged

The following models were included in the merge:

  • —/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/falcon-and-cc-qc-orig-10p/step62500
  • —/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/falcon-and-cc-qc-orig-10p/step57500
  • —/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/falcon-and-cc-qc-orig-10p/step60000
  • —/opt/tiger/PanSafetyBetterMeasurement/mergescalingckptscache/source_ckpts/falcon-and-cc-qc-orig-10p/step65000

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/falcon-and-cc-qc-orig-10p/step57500
  parameters:
    weight: 1
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/falcon-and-cc-qc-orig-10p/step60000
  parameters:
    weight: 2
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/falcon-and-cc-qc-orig-10p/step62500
  parameters:
    weight: 3
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/falcon-and-cc-qc-orig-10p/step65000
  parameters:
    weight: 4
- model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/falcon-and-cc-qc-orig-10p/step67500
  parameters:
    weight: 5
base_model: /opt/tiger/Pan_Safety_Better_Measurement/merge_scaling_ckpts_cache/source_ckpts/falcon-and-cc-qc-orig-10p/step67500
merge_method: linear
parameters:
  normalize: true
dtype: float32
out_dtype: bfloat16