Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- SicariusSicariiStuff/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct_Abliterated
|
| 5 |
+
tags:
|
| 6 |
+
- finetune
|
| 7 |
+
- llama
|
| 8 |
+
- occult
|
| 9 |
+
- uncensored
|
| 10 |
+
datasets:
|
| 11 |
+
- OccultAI/Matrix_77
|
| 12 |
+
language:
|
| 13 |
+
- en
|
| 14 |
+
library_name: transformers
|
| 15 |
+
widget:
|
| 16 |
+
- text: "Morpheus 8B v2"
|
| 17 |
+
output:
|
| 18 |
+
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/dZ-Q05tEZVM-W3nFIab6U.png
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
> [!CAUTION]
|
| 22 |
+
> <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.
|
| 23 |
+
>
|
| 24 |
+
|
| 25 |
+
# Morpheus 8B v2
|
| 26 |
+
|
| 27 |
+
**Recommended Settings:** Temp 1.0, TopNSigma 1.25
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
`{'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}`
|
| 32 |
+
|
| 33 |
+
- Morpheus v1 features 420 Morpheus Q&A, 100 Poe/Raven, and 145 Cthulhu. Average dataset token length 224.
|
| 34 |
+
- Morpheus v2 features 77 long context Matrix Q&A, generated from high quality source material. Average dataset token length 1044.
|