[!CAUTION] ⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Llama 3 chat template.

🦙 Llamatron 8B v1

This is a highly creative, uncensored merge of pre-trained language models created using mergekit.

There are a few refusals, but the censorship is so minimal that if you reswipe with moderate temp it often works. The model could still be ablated if needed.

Merge Details

Merge Method

This model was merged using the DELLA merge method using aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored as a base.

Models Merged

The following models were included in the merge:

• aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
• akjindal53244/Llama-3.1-Storm-8B
• Azazelle/Llama-3-LongStory-LORA
• Babsie/ThetaBlackGorgon-8B
• Bacon666/Athlon-8B-0.1
• DarkArtsForge/Raven-8B-v1
• EldritchLabs/Cthulhu-8B-v1.4
• Hastagaras/Jamet-8B-L3-MK.V-Blackroot
• juiceb0xc0de/bella-bartender-8b-llama3.1
• Naphula-Archives/mini-bella-test-nemotron-8B-LoRA
• NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
• OccultAI/Morpheus-8B-v1
• OccultAI/Morpheus-8B-v2
• OccultAI/Morpheus-8B-v3
• OpenPipe/Hermes-2-Theta-Llama-3-8B-32k
• Sao10K/L3-8B-Stheno-v3.2
• SicariusSicariiStuff/Assistant_Pepe_8B
• SicariusSicariiStuff/Dusk_Rainbow
• SicariusSicariiStuff/Impish_Mind_8B
• SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
• TroyDoesAI/BlackSheep-X-Dolphin

Configuration

The following YAML configuration was used to produce this model:

architecture: LlamaForCausalLM
base_model: B:\8B\!models--aifeifei798--DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored # B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
models:
  - model: B:\8B\!models--aifeifei798--DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
  - model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated@B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated\!Morpheus_v1_8B_finetuned_adapter\LoRA
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated@B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated\!Morpheus_v2_77_8B_finetuned_adapter\LoRA
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated@B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated\!Morpheus_v3_prototype_checkpoint_526
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated@B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated\!minibella_checkpoint-52
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated@B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated\!Raven_v1_8B_finetuned_adapter\checkpoint-125
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated@B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated\!Cthulhu_v1.4_8B_finetuned_adapter\LoRA
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\SicariusSicariiStuffAssistantPepe8B
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--OpenPipe--Hermes-2-Theta-Llama-3-8B-32k
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--Bacon666--Athlon-8B-0.1
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\juiceb0xc0de__bella-bartender-8b-llama3.1
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Dusk_Rainbow
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--Sao10K--L3-8B-Stheno-v3.2
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--akjindal53244--Llama-3.1-Storm-8B
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--aifeifei798--DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored@B:\8B\!models--Azazelle--Llama-3-LongStory-LORA
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--Babsie--ThetaBlackGorgon-8B
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--TroyDoesAI--BlackSheep-X-Dolphin
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--Hastagaras--Jamet-8B-L3-MK.V-Blackroot
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--NeverSleep--Llama-3-Lumimaid-8B-v0.1-OAS
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
  - model: B:\8B\!models--SicariusSicariiStuff--Impish_Mind_8B
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.099
# Seed: 420 
merge_method: della
parameters:
  lambda: 1.0
  normalize: false
  int8_mask: false
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: B:\8B\SicariusSicariiStuffAssistantPepe8B
chat_template: auto
name: 🦙‍ Llamatron-8B-v1