old-MakeGemma3

Note: multilingual feature improvement version has been posted. Please use Testament200156/MakeGemma3-abliterated. This location is currently deprecated. This is a merge of pre-trained language models created using mergekit. I have created a GGUF, so please check the GGUF folder. Since this is an experimental model, there are some defects, mainly in the multilingual functionality. Please use with caution.

Merge Details

Merge Method

This model was merged using the NuSLERP merge method.

Models Merged

The following models were included in the merge:

  • drwlf/medgemma-27b-it-abliterated
  • test_base (summykai/gemma3-27b-abliterated-dpo with additional layers added)

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: test_base
    parameters:
      weight: 1.0
  - model: medgemma-27b-it-abliterated
    parameters: 
      weight: 1.0
merge_method: nuslerp
dtype: bfloat16
Downloads last month
67
Safetensors
Model size
29B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support