Qwen2-11.3B

NOTE: This a model to be used for continued pretraining or finetuning! It is not a model to run on it's own. There will be some coming soon.

Perplexity measurements: PPL = 7.7614 +/- 0.10721

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:

• Qwen/Qwen2-7B

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 22]
    model: Qwen/Qwen2-7B
- sources:
  - layer_range: [6, 22]
    model: Qwen/Qwen2-7B
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [22, 28]
    model: Qwen/Qwen2-7B