merged_linear_v2

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using /models/qwen3-4b-instruct-2507 as a base.

Models Merged

The following models were included in the merge:

  • /models/game-top-ana4-4
  • /models/lgc-v2-top-train11
  • /models/print-top-0101928

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: /models/game-top-ana4-4
    parameters:
      weight: 0.33
  - model: /models/print-top-0101928
    parameters:
      weight: 0.33
  - model: /models/lgc-v2-top-train11
    parameters:
      weight: 0.34
merge_method: task_arithmetic
base_model: /models/qwen3-4b-instruct-2507
dtype: bfloat16
Downloads last month
16
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for Arielasgas/affine-merged-linear