ReallyFloppyPenguin's picture
Add merged model
88cb5ce verified
metadata
base_model:
  - Qwen/Qwen3-4B-Thinking-2507
  - Qwen/Qwen3-4B
library_name: transformers
tags:
  - mergekit
  - merge

Qwen3-Merged

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

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen3-4B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: Qwen/Qwen3-4B
    parameters:
      weight: 1.0
      density: 1.0
  - model: Qwen/Qwen3-4B-Thinking-2507
    parameters:
      weight: 0.3
      density: 0.5
merge_method: ties
base_model: Qwen/Qwen3-4B
dtype: bfloat16
parameters:
  normalize: true
  int8_mask: true