---
license: apache-2.0
base_model:
- SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
tags:
- finetune
- llama
- occult
- uncensored
datasets:
- OccultAI/Matrix_77
language:
- en
library_name: transformers
widget:
  - text: "Morpheus 8B v2"
    output:
      url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/dZ-Q05tEZVM-W3nFIab6U.png
---

> [!CAUTION]
> <span style="color:red; font-weight:bold">⚠️ Warning:</span> 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.
>

# Morpheus 8B v2

**Recommended Settings:** Temp 1.0, TopNSigma 1.25

![Morpheus](https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/dZ-Q05tEZVM-W3nFIab6U.png)

`{'loss': 0.862, 'grad_norm': 3.7123961448669434, 'learning_rate': 6.894700159171534e-05, 'entropy': 0.9889850616455078, 'num_tokens': 297120.0, 'mean_token_accuracy': 0.7658079862594604, 'epoch': 4.0}`

- Morpheus v1 features 420 Morpheus Q&A, 100 Poe/Raven, and 145 Cthulhu. Average dataset token length 224.
- Morpheus v2 features 77 long context Matrix Q&A, generated from high quality source material. Average dataset token length 1044.