Math-Mixtral-7B / README.md
DT12the's picture
Upload folder using huggingface_hub
f2c2f73 verified
metadata
base_model:
  - mistralai/Mistral-7B-Instruct-v0.2
  - meta-math/MetaMath-Mistral-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 TIES merge method using mistralai/Mistral-7B-Instruct-v0.2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: mistralai/Mistral-7B-Instruct-v0.2
    # No additional parameters needed for the base model
  - model: meta-math/MetaMath-Mistral-7B
    parameters:
      density: 0.7  # A higher density for MetaMath to prioritize its parameters for math questions
      weight: 0.7   # Higher weight to MetaMath to ensure its influence on math-related answers is strong
merge_method: ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
  normalize: true
dtype: float16