baban/Qwen2.5-merged

output_qwen

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/Qwen2.5-7B-Instruct as a base.

Models Merged

The following models were included in the merge:

• nguyentd/FinancialAdvice-Qwen2.5-7B
• shibing624/chinese-text-correction-7b
• nvidia/OpenCodeReasoning-Nemotron-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nvidia/OpenCodeReasoning-Nemotron-7B
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: shibing624/chinese-text-correction-7b
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
  - model: nguyentd/FinancialAdvice-Qwen2.5-7B
    parameters:
      density: 0.33
      weight:
        - filter: mlp
          value: 0.5
        - value: 0
merge_method: ties
base_model: Qwen/Qwen2.5-7B-Instruct
parameters:
  normalize: true
dtype: bfloat16