README.md

metadata

license: other
tags:
  - merge
  - mergekit
  - lazymergekit
  - deepseek-ai/deepseek-math-7b-rl
  - deepseek-ai/deepseek-math-7b-instruct

deep-wizard-7B-slerp

deep-wizard-7B-slerp is a merge of the following models using mergekit:

• deepseek-ai/deepseek-math-7b-rl
• deepseek-ai/deepseek-math-7b-instruct

🧩 Configuration

  models:
    - model: deepseek-ai/deepseek-math-7b-base
      # no parameters necessary for base model
    - model: deepseek-ai/deepseek-math-7b-rl
      parameters:
        density: 0.5
        weight: 0.7
    - model: deepseek-ai/deepseek-math-7b-instruct
      parameters:
        density: 0.5
        weight: 0.3
  merge_method: dare_ties
  base_model: deepseek-ai/deepseek-math-7b-base
  parameters:
    int8_mask: true
  dtype: bfloat16