bin4ry_stheno_8B_v1

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Sao10K/L3-8B-Stheno-v3.3-32K
• Hastagaras/For-Bin4ry

Configuration

The following YAML configuration was used to produce this model:

base_model: Hastagaras/For-Bin4ry
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 32]
    model: Hastagaras/For-Bin4ry
  - layer_range: [0, 32]
    model: Sao10K/L3-8B-Stheno-v3.3-32K