README.md

metadata

base_model:
  - ALBADDAWI/DeepCode-7B-Aurora-v3
  - AI-MO/NuminaMath-7B-TIR
  - deepseek-ai/deepseek-math-7b-base
  - deepseek-ai/deepseek-math-7b-rl
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 TIES merge method using deepseek-ai/deepseek-math-7b-base as a base.

Models Merged

The following models were included in the merge:

• ALBADDAWI/DeepCode-7B-Aurora-v3
• AI-MO/NuminaMath-7B-TIR
• deepseek-ai/deepseek-math-7b-rl

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: AI-MO/NuminaMath-7B-TIR
    parameters:
      density: 1
      weight: 0.35
  - model: deepseek-ai/deepseek-math-7b-rl
    parameters:
      density: 1
      weight: 0.3
  - model: ALBADDAWI/DeepCode-7B-Aurora-v3
    parameters:
      density: 1
      weight: 0.35
merge_method: ties
base_model: deepseek-ai/deepseek-math-7b-base
parameters:
  normalize: true
dtype: float16