TareksGraveyard/Doppleganger-V7-LLaMa-70B

merge

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

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using NaniDAO/Llama-3.3-70B-Instruct-ablated 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

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: flammenai/Mahou-1.5-llama3.1-70B
    parameters:
      weight: 0.25
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: flammenai/Llama3.1-Flammades-70B
    parameters:
      weight: 0.25
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B
    parameters:
      weight: 0.25
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: NaniDAO/Llama-3.3-70B-Instruct-ablated
    parameters:
      weight: 0.25
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
merge_method: della_linear
base_model: NaniDAO/Llama-3.3-70B-Instruct-ablated
parameters:
  epsilon: 0.2
  lambda: 1.1
  normalize: false
dtype: bfloat16
tokenizer:
 source: base