TareksGraveyard/Z-MODEL3-V1-SCE

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using TareksLab/Braniac-V3-LLaMa-70B as a base.

Models Merged

The following models were included in the merge:

• Mawdistical/Lured-Lapine-70B
• Sao10K/L3.1-70B-Hanami-x1
• EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
• nbeerbower/Llama3.1-Gutenberg-Doppel-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      select_topk: 0.5
  - model: Sao10K/L3.1-70B-Hanami-x1
    parameters:
      select_topk: 0.5
  - model: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
    parameters:
      select_topk: 0.5
  - model: Mawdistical/Lured-Lapine-70B
    parameters:
      select_topk: 0.5
  - model: TareksLab/Braniac-V3-LLaMa-70B
    parameters:
      select_topk: 0.5
base_model: TareksLab/Braniac-V3-LLaMa-70B
merge_method: sce
parameters:
  int8_mask: true  
tokenizer:
  source: union
chat_template: llama3
dtype: bfloat16