35 lines
1.2 KiB
Markdown
35 lines
1.2 KiB
Markdown
---
|
|
license: apache-2.0
|
|
base_model:
|
|
- SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
|
|
tags:
|
|
- finetune
|
|
- llama
|
|
- occult
|
|
- uncensored
|
|
datasets:
|
|
- OccultAI/Morpheus_665
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
widget:
|
|
- text: "Morpheus 8B v1"
|
|
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 v1
|
|
|
|
**Recommended Settings:** Temp 1.0, TopNSigma 1.25
|
|
|
|
|
|
|
|
`{'loss': 0.5651, 'grad_norm': 3.787045478820801, 'learning_rate': 1.0386570913148586e-05, 'entropy': 0.7085917145013809, 'num_tokens': 588832.0, 'mean_token_accuracy': 0.8508399426937103, 'epoch': 4.0}`
|
|
|
|
| Model | Q0 Score | Quant | Q0G | Refusals |
|
|
| :--- | :--- | :--- | :--- | :--- |
|
|
| Morpheus 8B v1 | 15365 | Q6_K | Pass | 0/100 | |