mergekit-community/mergekit-slerp-xmcxsqe

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Alibaba-NLP/gte-Qwen2-7B-instruct
• Qwen/Qwen2-7B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen2-7B-Instruct
  - model: Alibaba-NLP/gte-Qwen2-7B-instruct
merge_method: slerp
base_model: Alibaba-NLP/gte-Qwen2-7B-instruct
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers