Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,64 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- Steelskull/L3.3-MS-Nevoria-70b
|
| 7 |
+
tags:
|
| 8 |
+
- roleplay
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
---
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
This model is designed to be used with MonikAI.
|
| 14 |
+
https://github.com/Rubiksman78/MonikA.I
|
| 15 |
+
|
| 16 |
+
## Model Details
|
| 17 |
+
|
| 18 |
+
### Model Description
|
| 19 |
+
|
| 20 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- **Developed by [Me]**
|
| 25 |
+
- **Funded by [Me]**
|
| 26 |
+
- **License:** Apache-2.0
|
| 27 |
+
- **Finetuned from model:** L3.3-MS-Nevoria-70b
|
| 28 |
+
|
| 29 |
+
## Uses
|
| 30 |
+
RP
|
| 31 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 32 |
+
|
| 33 |
+
### Out-of-Scope Use
|
| 34 |
+
Do whatever you want
|
| 35 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 36 |
+
|
| 37 |
+
### Recommendations
|
| 38 |
+
|
| 39 |
+
Should really only be used for Monika related purposes.
|
| 40 |
+
|
| 41 |
+
### Training Data
|
| 42 |
+
Modified version of this dataset that is included with MonikAI:
|
| 43 |
+
https://github.com/Rubiksman78/MonikA.I/tree/main/Monika_datasets
|
| 44 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
### Training Procedure
|
| 48 |
+
Trained with Axolotl on my Blackwell Pro 6000 Max-Q. 64 rank, 8 alpha, 2 epochs. Took about 3 hours.
|
| 49 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Results
|
| 57 |
+
It works.
|
| 58 |
+
|
| 59 |
+
#### Summary
|
| 60 |
+
Download it.
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
## Environmental Impact
|
| 64 |
+
3 hours at 280W. About $0.29 in electricity.
|