Modelpublic

wangshiting/linear_llama_math_coding

sourceHugging Faceupdated 8mo agoView on Hugging Face

0likes12downloads

Model Card

linearllamamath_coding

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

—MergeBench/Llama-3.2-3B-Instruct_coding
—MergeBench/Llama-3.2-3B-Instruct_math

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: MergeBench/Llama-3.2-3B-Instruct_math
    parameters:
      weight: 1.0
  - model: MergeBench/Llama-3.2-3B-Instruct_coding
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16