sometimesanotion/Abliterate-Qwenvergence

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using arcee-ai/Virtuoso-Small as a base.

Models Merged

The following models were included in the merge:

• huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2

Configuration

The following YAML configuration was used to produce this model:

name:                Qwenvergence-Abliterate
merge_method:        dare_ties
base_model:          arcee-ai/Virtuoso-Small
tokenizer_source:    arcee-ai/Virtuoso-Small
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
  density:           1.00
  weight:            1.00
slices:
  - sources:
      - model:       huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
        parameters: 
          density:   1.00
          weight:    1.00
        layer_range: [ 0, 8 ]
      - model:       arcee-ai/Virtuoso-Small
        parameters: 
          density:   1.00
          weight:    0.00
        layer_range: [ 0, 8 ]
  - sources:
      - model:       huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
        parameters: 
          density:   1.00
          weight:    1.00
        layer_range: [ 8, 16 ]
      - model:       arcee-ai/Virtuoso-Small
        parameters: 
          density:   1.00
          weight:    0.00
        layer_range: [ 8, 16 ]
  - sources:
      - model:       huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
        parameters: 
          density:   1.00
          weight:    1.00
        layer_range: [ 16, 24 ]
      - model:       arcee-ai/Virtuoso-Small
        parameters: 
          density:   1.00
          weight:    0.00
        layer_range: [ 16, 24 ]
  - sources:
      - model:       huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
        parameters: 
          density:   1.00
          weight:    1.00
        layer_range: [ 24, 32 ]
      - model:       arcee-ai/Virtuoso-Small
        parameters: 
          density:   1.00
          weight:    0.00
        layer_range: [ 24, 32 ]
  - sources:
      - model:       huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
        parameters: 
          density:   1.00
          weight:    1.00
        layer_range: [ 32, 40 ]
      - model:       arcee-ai/Virtuoso-Small
        parameters: 
          density:   1.00
          weight:    0.00
        layer_range: [ 32, 40 ]
  - sources:
      - model:       huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
        parameters: 
          density:   1.00
          weight:    1.00
        layer_range: [ 40, 48 ]
      - model:       arcee-ai/Virtuoso-Small
        parameters: 
          density:   1.00
          weight:    0.00
        layer_range: [ 40, 48 ]
dtype:               bfloat16
out_dtype:           bfloat16