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:

A very coherent but completely uncensored base
A very intelligent model based on UGI, Willingness and NatInt scores on the UGI Leaderboard
A highly descriptive writing model, specializing in creative and natural prose
A RP model specially merged with fine-tuned models that use a lot of RP datasets
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:

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

Merge Details

Merge Method

This model was merged using the NearSwap merge method using TareksLab/M-NS-STEP3 as a base.

Models Merged

The following models were included in the merge:

TareksLab/M-MERGE4

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
      - model: TareksLab/M-MERGE4
      - model: TareksLab/M-NS-STEP3
merge_method: nearswap
base_model: TareksLab/M-NS-STEP3
parameters:
  t:
    - value: 0.0001
dtype: bfloat16
tokenizer:
 source: base

TareksTesting/Legion-V1.1-LLaMa-70B

Merge Details

Merge Method

Models Merged

Configuration

TareksTesting/
Legion-V1.1-LLaMa-70B