metadata

base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

Qwen2.5-14B-Instruct-MIX48

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:

/models/14b-code-execution-15k-400steps-lr1e-5-2-blocks
/models/14b-r1-sdg-all-public-2m-8epochs-lr1e-4-minlr1e-7-warm1600

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /models/14b-code-execution-15k-400steps-lr1e-5-2-blocks
    parameters:
      weight: 0.7
  - model: /models/14b-r1-sdg-all-public-2m-8epochs-lr1e-4-minlr1e-7-warm1600
    parameters:
      weight: 0.3
merge_method: linear
dtype: bfloat16