bunnycore/Mixtronix-8B

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using nvidia/Mistral-NeMo-Minitron-8B-Base as a base.

Models Merged

The following models were included in the merge:

• nvidia/Mistral-NeMo-Minitron-8B-Instruct
• rasyosef/Mistral-NeMo-Minitron-8B-Chat
• Delta-Vector/Tor-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: rasyosef/Mistral-NeMo-Minitron-8B-Chat
    parameters:
      weight: 1
      density: 1

  - model: Delta-Vector/Tor-8B
    parameters:
      weight: 1
      density: 1
      
  - model: nvidia/Mistral-NeMo-Minitron-8B-Instruct
    parameters:
      weight: 1
      density: 1

merge_method: ties
base_model: nvidia/Mistral-NeMo-Minitron-8B-Base
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16