djuna-test-lab / TEST-Q2.5-AA

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:

• allura-org/Teleut-7b
• EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 4]
    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
- sources:
  - layer_range: [3, 4] 
    model: allura-org/Teleut-7b
- sources:
  - layer_range: [4, 8]
    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
- sources:
  - layer_range: [7, 8]
    model: allura-org/Teleut-7b
- sources:
  - layer_range: [8, 12]
    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
- sources:
  - layer_range: [11, 12]
    model: allura-org/Teleut-7b
- sources:
  - layer_range: [12, 16]
    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
- sources:
  - layer_range: [15, 16]
    model: allura-org/Teleut-7b
- sources:
  - layer_range: [16, 20]
    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
- sources:
  - layer_range: [19, 20]
    model: allura-org/Teleut-7b
- sources:
  - layer_range: [20, 28]
    model: EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1
merge_method: passthrough
dtype: bfloat16