ft-no-repeat-write-merge-rp-only

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 meta-llama/Meta-Llama-3.1-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• Hastagaras/Llama-3.1-Jamet-8B-MK.I
• crestf411/L3.1-8B-sunfall-v0.6.1-dpo
• leosheng/no-repeat-write

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: meta-llama/Meta-Llama-3.1-8B-Instruct
  - model: crestf411/L3.1-8B-sunfall-v0.6.1-dpo # Another RP Model trained on... stuff
    parameters:
      density: 0.4
      weight: 0.3
  - model: Hastagaras/Llama-3.1-Jamet-8B-MK.I  # Another RP / Storytelling Model
    parameters:
      density: 0.5
      weight: 0.3
  # - model: maldv/badger-iota-llama-3-8b #Megamerge - Helps with General Knowledge
  #   parameters:
  #     density: 0.6
  #     weight: 0.5
  - model: leosheng/no-repeat-write
    parameters:
      density: 0.7
      weight: 0.4
merge_method: ties
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
parameters:
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16