TareksTesting/Legion-V1.2-LLaMa-70B

~ We are Legion...

My biggest merge yet, consisting of a total of 15 specially curated models. My methodology in approaching this was to create 5 highly specialized models:

1. A very coherent but completely uncensored base
2. A very intelligent model based on UGI, Willingness and NatInt scores on the UGI Leaderboard
3. A highly descriptive writing model, specializing in creative and natural prose
4. A RP model specially merged with fine-tuned models that use a lot of RP datasets
5. The secret ingredient: A completely unhinged, uncensored final model

These five models went through a series of iterations until I got something I thought worked well and then combined them to make LEGION.

The full list of models used in this merge is below:

• TheDrummer/Fallen-Llama-3.3-R1-70B-v1
• Sao10K/L3-70B-Euryale-v2.1
• SicariusSicariiStuff/Negative_LLAMA_70B
• allura-org/Bigger-Body-70b
• Sao10K/70B-L3.3-mhnnn-x1
• Sao10K/L3.3-70B-Euryale-v2.3
• Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
• Sao10K/L3.1-70B-Hanami-x1
• EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
• TheDrummer/Anubis-70B-v1
• ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4
• LatitudeGames/Wayfarer-Large-70B-Llama-3.3
• NeverSleep/Lumimaid-v0.2-70B
• ReadyArt/Forgotten-Safeword-70B-3.6
• huihui-ai/Llama-3.3-70B-Instruct-abliterated

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using TareksLab/M-BASE-SCE as a base.

Models Merged

The following models were included in the merge:

• TareksLab/M-MERGE4
• TareksLab/M-MERGE1
• TareksLab/M-MERGE2
• TareksLab/M-MERGE3

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TareksLab/M-MERGE4
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/M-MERGE2
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/M-MERGE3
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/M-MERGE1
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/M-BASE-SCE
    parameters:
      weight: 0.20
      density: 0.5
merge_method: dare_ties
base_model: TareksLab/M-BASE-SCE
parameters:
  normalize: false
out_dtype: bfloat16
tokenizer:
 source: base