TareksGraveyard/MO-MODEL4-V0.1-LLaMa-70B

MERGE2

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 Tarek07/Dungeonmaster-V2.2-Expanded-LLaMa-70B as a base.

Models Merged

The following models were included in the merge:

• flammenai/Llama3.1-Flammades-70B
• SentientAGI/Dobby-Unhinged-Llama-3.3-70B
• flammenai/Mahou-1.5-llama3.1-70B
• nbeerbower/Llama3.1-Gutenberg-Doppel-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: flammenai/Mahou-1.5-llama3.1-70B
    parameters:
      select_topk: 0.75
  - model: flammenai/Llama3.1-Flammades-70B
    parameters:
      select_topk: 0.75
  - model: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
    parameters:
      select_topk: 0.75
  - model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B
    parameters:
      select_topk: 0.75
  - model: Tarek07/Dungeonmaster-V2.2-Expanded-LLaMa-70B
    parameters:
      select_topk: 0.75
base_model: Tarek07/Dungeonmaster-V2.2-Expanded-LLaMa-70B
merge_method: sce
parameters:
  int8_mask: true
tokenizer:
  source: union
chat_template: llama3
dtype: float32
out_dtype: bfloat16