TareksLab/Lascivious-LLaMa-70B

While I was trying a new merge method for my Tarek07/Progenitor-V1.2-LLaMa-70B model, I noticed a substantial increase in the models proclivity for more NSFW themes. I then had the idea to try and merge the most 'nsfw' models I know in the same way and see how it turns out. Still Testing.

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 nbeerbower/Llama-3.1-Nemotron-lorablated-70B as a base.

Models Merged

The following models were included in the merge:

• Nohobby/L3.3-Prikol-70B-v0.3
• NeverSleep/Lumimaid-v0.2-70B
• Sao10K/70B-L3.3-mhnnn-x1
• Sao10K/L3.1-70B-Hanami-x1
• SicariusSicariiStuff/Negative_LLAMA_70B

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
  # Target models
  - model: NeverSleep/Lumimaid-v0.2-70B
  - model: Sao10K/L3.1-70B-Hanami-x1
  - model: Sao10K/70B-L3.3-mhnnn-x1
  - model: Nohobby/L3.3-Prikol-70B-v0.3
merge_method: sce
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
parameters:
  select_topk: 1.0
dtype: bfloat16