image/png An experimental frankenmerge (upscaled) model.

merge

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

Merge Details

Merge Method

This model was merged using the Passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: passthrough
dtype: bfloat16
slices:
  - sources:
    - model: yamatazen/Ayla-Light-12B-Stock
      layer_range: [0,40]
  - sources:
    - model: yamatazen/Ayla-Light-12B-Stock
      layer_range: [16,24]
Downloads last month
21
Safetensors
Model size
14.4B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for yamatazen/Ayla-Light-Extra

Finetuned
(3)
this model
Quantizations
2 models