Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,44 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
license_name: concedo
|
| 4 |
-
license_link: LICENSE
|
| 5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: concedo
|
| 4 |
+
license_link: LICENSE
|
| 5 |
+
---
|
| 6 |
+
<div align="center">
|
| 7 |
+
|
| 8 |
+
# Phi-SoSerious-Mini-V1
|
| 9 |
+
</div>
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
# Let's put a smile on that face!
|
| 14 |
+
|
| 15 |
+
This is a finetune of https://huggingface.co/microsoft/Phi-3-mini-4k-instruct trained on a variant of the Kobble Dataset.
|
| 16 |
+
Training was done in under 4 hours on a single Nvidia RTX 3090 GPU with qLora (LR 1.2e-4, rank 16, alpha 16, batch size 3, gradient acc. 3, 2048 ctx).
|
| 17 |
+
|
| 18 |
+
You can obtain the GGUF quantization of this model here:
|
| 19 |
+
|
| 20 |
+
## Dataset and Objectives
|
| 21 |
+
|
| 22 |
+
The Kobble Dataset is a semi-private aggregated dataset made from multiple online sources and web scrapes, augmented with some synthetic data.
|
| 23 |
+
It contains content chosen and formatted specifically to work with KoboldAI software and Kobold Lite.
|
| 24 |
+
The objective of this model was to produce a usable version of Phi-3-mini usable for storywriting, conversations and instructions, and without excess tendency for refsual.
|
| 25 |
+
|
| 26 |
+
#### Dataset Categories:
|
| 27 |
+
- Instruct: Single turn instruct examples presented in the Alpaca format, with an emphasis on uncensored and unrestricted responses.
|
| 28 |
+
- Chat: Two participant roleplay conversation logs in a multi-turn raw chat format that KoboldAI uses.
|
| 29 |
+
- Story: Unstructured fiction excerpts, including literature containing various erotic and provocative content.
|
| 30 |
+
|
| 31 |
+
<!-- prompt-template start -->
|
| 32 |
+
## Prompt template: Alpaca
|
| 33 |
+
|
| 34 |
+
```
|
| 35 |
+
### Instruction:
|
| 36 |
+
{prompt}
|
| 37 |
+
|
| 38 |
+
### Response:
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
<!-- prompt-template end -->
|
| 42 |
+
|
| 43 |
+
**Note:** *No assurances will be provided about the **origins, safety, or copyright status** of this model, or of **any content** within the Kobble dataset.*
|
| 44 |
+
*If you belong to a country or organization that has strict AI laws or restrictions against unlabelled or unrestricted content, you are advised not to use this model.*
|