alexxi19/ft-v1-violet-merge

merged_llm

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 alexxi19/ft-v1-violet as a base.

Models Merged

The following models were included in the merge:

• anthracite-org/magnum-v2-12b

Configuration

The following YAML configuration was used to produce this model:

models:
  # - model: meta-llama/Meta-Llama-3.1-8B-Instruct
  # - model: Epiculous/Violet_Twilight-v0.2 # Another RP Model trained on... stuff
  #   parameters:
  #     density: 0.4
  #     weight: 0.4
  - model: anthracite-org/magnum-v2-12b  # Another RP / Storytelling Model
    parameters:
      density: 0.4
      weight: 0.4
  # - model: maldv/badger-iota-llama-3-8b #Megamerge - Helps with General Knowledge
  #   parameters:
  #     density: 0.6
  #     weight: 0.5
  - model: alexxi19/ft-v1-violet
    parameters:
      density: 0.7
      weight: 0.6
merge_method: ties
base_model: alexxi19/ft-v1-violet
parameters:
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
chat_template: chatml