ehristoforu/testq-32b

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:

• ehristoforu/fq2.5-32b-v1

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 16]
    model: ehristoforu/fq2.5-32b-v1
- sources:
  - layer_range: [8, 24]
    model: ehristoforu/fq2.5-32b-v1
- sources:
  - layer_range: [16, 32]
    model: ehristoforu/fq2.5-32b-v1
- sources:
  - layer_range: [24, 40]
    model: ehristoforu/fq2.5-32b-v1
- sources:
  - layer_range: [32, 48]
    model: ehristoforu/fq2.5-32b-v1
- sources:
  - layer_range: [40, 56]
    model: ehristoforu/fq2.5-32b-v1
- sources:
  - layer_range: [48, 64]
    model: ehristoforu/fq2.5-32b-v1
merge_method: passthrough
dtype: bfloat16
tokenizer_source: "Qwen/Qwen2.5-32B-Instruct"