JackCloudman/QwQ-56B-Ghost-GGUF

QwQ-56B-Ghost is an extended model derived from Qwen-32B-Preview-Jackterated using the merging passthrough technique inspired in models like miqu-1-120b. The result is a ~56B parameter model

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• JackCloudman/QwQ-32B-Preview-jackterated

Configuration

The following YAML configuration was used to produce this model:

dtype: float16
merge_method: passthrough
slices:
  - sources:
      - layer_range: [0, 16]
        model: JackCloudman/QwQ-32B-Preview-jackterated
  - sources:
      - layer_range: [8, 24]
        model: JackCloudman/QwQ-32B-Preview-jackterated
  - sources:
      - layer_range: [16, 32]
        model: JackCloudman/QwQ-32B-Preview-jackterated
  - sources:
      - layer_range: [24, 40]
        model: JackCloudman/QwQ-32B-Preview-jackterated
  - sources:
      - layer_range: [32, 48]
        model: JackCloudman/QwQ-32B-Preview-jackterated
  - sources:
      - layer_range: [40, 56]
        model: JackCloudman/QwQ-32B-Preview-jackterated
  - sources:
      - layer_range: [48, 64]
        model: JackCloudman/QwQ-32B-Preview-jackterated

Credits

• Qwen and QwQ-32B-Preview
• @FailSpy notebook with abliterate technique
• Mergekit
• Archive
• You :D