---
base_model:
- TareksLab/M-NS-STEP3
- TareksLab/M-MERGE4
library_name: transformers
tags:
- mergekit
- merge
- not-for-all-audiences
license: llama3.3
---
*~ 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](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1)
* [Sao10K/L3-70B-Euryale-v2.1](https://huggingface.co/Sao10K/L3-70B-Euryale-v2.1)
* [SicariusSicariiStuff/Negative_LLAMA_70B](https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B)
* [allura-org/Bigger-Body-70b](https://huggingface.co/allura-org/Bigger-Body-70b)
* [Sao10K/70B-L3.3-mhnnn-x1](https://huggingface.co/Sao10K/70B-L3.3-mhnnn-x1)
* [Sao10K/L3.3-70B-Euryale-v2.3](https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3)
* [Doctor-Shotgun/L3.3-70B-Magnum-v4-SE](https://huggingface.co/Doctor-Shotgun/L3.3-70B-Magnum-v4-SE)
* [Sao10K/L3.1-70B-Hanami-x1](https://huggingface.co/Sao10K/L3.1-70B-Hanami-x1)
* [EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1](https://huggingface.co/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1)
* [TheDrummer/Anubis-70B-v1](https://huggingface.co/TheDrummer/Anubis-70B-v1)
* [ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4](https://huggingface.co/ArliAI/Llama-3.3-70B-ArliAI-RPMax-v1.4)
* [LatitudeGames/Wayfarer-Large-70B-Llama-3.3](https://huggingface.co/LatitudeGames/Wayfarer-Large-70B-Llama-3.3)
* [NeverSleep/Lumimaid-v0.2-70B](https://huggingface.co/NeverSleep/Lumimaid-v0.2-70B)
* [ReadyArt/Forgotten-Safeword-70B-3.6](https://huggingface.co/ReadyArt/Forgotten-Safeword-70B-3.6)
* [huihui-ai/Llama-3.3-70B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated)

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [NearSwap](https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001) merge method using [TareksLab/M-NS-STEP3](https://huggingface.co/TareksLab/M-NS-STEP3) as a base.

### Models Merged

The following models were included in the merge:
* [TareksLab/M-MERGE4](https://huggingface.co/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
```