README.md

metadata

base_model:
  - happzy2633/qwen2.5-7b-ins-v3
  - AIDC-AI/Marco-o1
  - djuna/Q2.5-Fuppavy-7B
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• happzy2633/qwen2.5-7b-ins-v3
• AIDC-AI/Marco-o1
• djuna/Q2.5-Fuppavy-7B

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 8]
    model: AIDC-AI/Marco-o1
- sources:
  - layer_range: [4, 12]
    model: djuna/Q2.5-Fuppavy-7B
- sources:
  - layer_range: [9, 16]
    model: happzy2633/qwen2.5-7b-ins-v3
- sources:
  - layer_range: [13, 20]
    model: AIDC-AI/Marco-o1
- sources:
  - layer_range: [17, 24]
    model: djuna/Q2.5-Fuppavy-7B
- sources:
  - layer_range: [21, 28]
    model: happzy2633/qwen2.5-7b-ins-v3
merge_method: passthrough
dtype: bfloat16