Aaryan-Nakhat/experiment-37-prompt-5-guardrails-finetuning-itr-4-merged-exp-31-32

experiment_37

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

Merge Details

Merge Method

This model was merged using the linear DARE merge method using HuggingFaceH4/zephyr-7b-beta as a base.

Models Merged

The following models were included in the merge:

• Aaryan-Nakhat/experiment-31-prompt-5-guardrails-finetuning-itr-4-sub-prompt-1
• Aaryan-Nakhat/experiment-32-prompt-5-guardrails-finetuning-itr-4-sub-prompt-2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Aaryan-Nakhat/experiment-31-prompt-5-guardrails-finetuning-itr-4-sub-prompt-1
    parameters:
      weight: 0.5
  - model: Aaryan-Nakhat/experiment-32-prompt-5-guardrails-finetuning-itr-4-sub-prompt-2
    parameters:
      weight: 0.5
base_model: HuggingFaceH4/zephyr-7b-beta
merge_method: dare_linear
dtype: float16