axeron-forge-d2012984/README.md

base_model, library_name, tags

base_model	library_name	tags
Qwen/Qwen2.5-7B Qwen/Qwen2.5-7B-Instruct	transformers	forgelm forge

d2012984-b791-4cc3-882d-7ab77d3415b5

This is a forge of pre-trained language models created using forgelm.

Forge Details

Forge Method

This model was forged using the Task Arithmetic forge method using Qwen/Qwen2.5-7B as a base.

Models Forged

The following models were included in the forge:

• Qwen/Qwen2.5-7B-Instruct

Configuration

The following YAML configuration was used to produce this model:

base_model: Qwen/Qwen2.5-7B
dtype: bfloat16
forge_method: task_arithmetic
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 28]
        model: Qwen/Qwen2.5-7B-Instruct
        parameters:
          weight: 1.0
      - layer_range: [0, 28]
        model: Qwen/Qwen2.5-7B
tokenizer:
  source: base