README.md

metadata

base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

mergercoder

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 /home/hammh0a/EXP2_models/Base as a base.

Models Merged

The following models were included in the merge:

• /home/hammh0a/EXP2_models/Qwen2.5-7B-Instruct-SFT-merged.safetensors
• /home/hammh0a/EXP2_models/Qwen2.5-7B-Instruct-Reasoning-merged.safetensors

Configuration

The following YAML configuration was used to produce this model:

base_model: /home/hammh0a/EXP2_models/Base
models:
  - model: /home/hammh0a/EXP2_models/Qwen2.5-7B-Instruct-Reasoning-merged.safetensors
    parameters:
      weight: 1.0
  - model: /home/hammh0a/EXP2_models/Qwen2.5-7B-Instruct-SFT-merged.safetensors
    parameters:
      weight: -1.0
merge_method: task_arithmetic
dtype: bfloat16 

arxiv.org/abs/2509.01363