Qwen2.5-7B-M-v1

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 KoFinanceLLM/Qwen2.5-7B-CPT-Merge as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-7B-Instruct
• KoFinanceLLM/KRX-Qwen2.5-7B-SFT-MultiHiertt

Configuration

The following YAML configuration was used to produce this model:

base_model: KoFinanceLLM/Qwen2.5-7B-CPT-Merge
dtype: bfloat16
merge_method: ties
parameters:
  density: 1.0
  int8_mask: 1.0
  normalize: 1.0
  weight: 1.0
slices:
- sources:
  - layer_range: [0, 28]
    model: KoFinanceLLM/KRX-Qwen2.5-7B-SFT-MultiHiertt
    parameters:
      density: 1.0
      weight: 1.0
  - layer_range: [0, 28]
    model: Qwen/Qwen2.5-7B-Instruct
    parameters:
      density: 1.0
      weight: 1.0
  - layer_range: [0, 28]
    model: KoFinanceLLM/Qwen2.5-7B-CPT-Merge