mrcuddle/Unbound-Llama3-8B

merge

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

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using winglian/llama-3-8b-1m-PoSE as a base.

Models Merged

The following models were included in the merge:

• jondurbin/bagel-8b-v1.0
• aifeifei798/llama3-8B-DarkIdol-2.3-Uncensored-32K
• Deev124/hermes-llama3-roleplay-4000-v1
• vicgalle/Roleplay-Llama-3-8B
• DevsDoCode/LLama-3-8b-Uncensored
• vicgalle/Unsafe-Llama-3-8B
• Gryphe/Pantheon-RP-1.0-8b-Llama-3
• Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
• NeverSleep/Llama-3-Lumimaid-8B-v0.1
• Undi95/Llama-3-LewdPlay-8B-evo
• vicgalle/Humanish-Roleplay-Llama-3.1-8B
• mergekit-community/because_im_bored_nsfw1
• mlabonne/Hermes-3-Llama-3.1-8B-lorablated

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: aifeifei798/llama3-8B-DarkIdol-2.3-Uncensored-32K
    parameters:
      density: 0.65
      weight: 0.15
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1
    parameters:
      density: 0.70
      weight: 0.20
  - model: mergekit-community/because_im_bored_nsfw1
    parameters:
      density: 0.60
      weight: 0.10
  - model: jondurbin/bagel-8b-v1.0
    parameters:
      density: 0.60
      weight: 0.10
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
    parameters:
      density: 0.65
      weight: 0.15
  - model: Undi95/Llama-3-LewdPlay-8B-evo
    parameters:
      density: 0.75
      weight: 0.25
  - model: Deev124/hermes-llama3-roleplay-4000-v1
    parameters:
      density: 0.60
      weight: 0.10
  - model: DevsDoCode/LLama-3-8b-Uncensored
    parameters:
      density: 0.60
      weight: 0.10
  - model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated
    parameters:
      density: 0.65
      weight: 0.15
  - model: vicgalle/Roleplay-Llama-3-8B
    parameters:
      density: 0.70
      weight: 0.20
  - model: Gryphe/Pantheon-RP-1.0-8b-Llama-3
    parameters:
      density: 0.70
      weight: 0.20
  - model: vicgalle/Humanish-Roleplay-Llama-3.1-8B
    parameters:
      density: 0.70
      weight: 0.20
  - model: vicgalle/Unsafe-Llama-3-8B
    parameters:
      density: 0.70
      weight: 0.20
  - model: winglian/llama-3-8b-1m-PoSE
    parameters:
      density: 0.70
      weight: 0.20

merge_method: task_arithmetic
base_model: winglian/llama-3-8b-1m-PoSE
parameters:
  normalize: true
  int8_mask: true
dtype: float16