sonnet1

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 Qwen/Qwen3-32B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen3-32B
dtype: bfloat16
merge_method: dare_ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 64]
        model: fakemoonlo/Affine-5FnfLT3ntQXDsAnVC5H5WNQYVTY7SSCbxU3kxqhNybtJeNGb
        parameters:
          density: 0.7
          weight: 0.4
      - layer_range: [0, 64]
        model: michael-chan-000/affine-5Eh8v9zUpcBwNLRzE3bRv2FFhnaNPERRLdvEH8SdwLiahUh8
        parameters:
          density: 0.5
          weight: 0.35
      - layer_range: [0, 64]
        model: leary-comos/affine-5CFnCUCy5jDjXFQJV5L58Wi8wwyp1b9Xe2fQ9iaSfiFdkR1X
        parameters:
          density: 0.5
          weight: 0.25
      - layer_range: [0, 64]
        model: Qwen/Qwen3-32B
parameters:
  int8_mask: 1.0
Downloads last month
6
Safetensors
Model size
33B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ajtaltarabukin2022/sonnet1

Paper for ajtaltarabukin2022/sonnet1