merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mergekit-community/mergekit-passthrough-vsvihrr as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: model_stock
base_model: mergekit-community/mergekit-passthrough-vsvihrr
slices:
  - sources:
    - model: mergekit-community/mergekit-passthrough-vsvihrr
      layer_range: [0, 40]
    - model: mergekit-community/mergekit-model_stock-mhvxkzw
      layer_range: [0, 40]
    - model: mergekit-community/mergekit-model_stock-rxtwhlc
      layer_range: [0, 40]

  - sources:
    - model: mergekit-community/mergekit-passthrough-vsvihrr
      layer_range: [40, 60]
    - model: mergekit-community/mergekit-model_stock-rxtwhlc
      layer_range: [0, 20]
    - model: mergekit-community/mergekit-model_stock-mhvxkzw
      layer_range: [0, 20]

  - sources:
    - model: mergekit-community/mergekit-passthrough-vsvihrr
      layer_range: [60, 79]
    - model: mergekit-community/mergekit-model_stock-rxtwhlc
      layer_range: [21, 40]
    - model: mergekit-community/mergekit-model_stock-mhvxkzw
      layer_range: [21, 40]
Downloads last month
3
Safetensors
Model size
22.9B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mergekit-community/mergekit-model_stock-jkczmro