r4at/RuAdapt-HomerCreativeAnvita-Mix-Qw7B-v1

merge

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:

• RefalMachine/ruadapt_qwen2.5_7B_ext_u48_instruct
• suayptalha/HomerCreativeAnvita-Mix-Qw7B

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: RefalMachine/ruadapt_qwen2.5_7B_ext_u48_instruct
    layer_range: [0, 28]
  - model: suayptalha/HomerCreativeAnvita-Mix-Qw7B
    layer_range: [0, 28]
merge_method: slerp
base_model: suayptalha/HomerCreativeAnvita-Mix-Qw7B
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6]
  - filter: mlp
    value: [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6]
  - value: 0.1
dtype: bfloat16