Commit
·
ad3d527
1
Parent(s):
f8b7974
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,36 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
datasets:
|
| 4 |
-
- cross-hedgehog/autotrain-data-rose2
|
| 5 |
metrics:
|
| 6 |
- character
|
| 7 |
library_name: keras
|
| 8 |
tags:
|
| 9 |
- chat
|
| 10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
| 3 |
metrics:
|
| 4 |
- character
|
| 5 |
library_name: keras
|
| 6 |
tags:
|
| 7 |
- chat
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# training
|
| 11 |
+
## minimum
|
| 12 |
+
* python3
|
| 13 |
+
* tensorflow
|
| 14 |
+
* numpy
|
| 15 |
+
* pandas
|
| 16 |
+
* at least 1gb of ram
|
| 17 |
+
* a lot of patience
|
| 18 |
+
|
| 19 |
+
# commands
|
| 20 |
+
python main.py
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
# dataset:
|
| 24 |
+
## origin
|
| 25 |
+
* based on 'danganronpa: trigger happy havoc'
|
| 26 |
+
* chatgpt
|
| 27 |
+
|
| 28 |
+
# scope
|
| 29 |
+
a simple-ish ai model for cahtting with Chihiro Fujisaki
|
| 30 |
+
i have no idea how to expand the initial_data.csv(has a couple of things, but it is nowhere near perfect), so i might not update this, or i will, its up to fate at the moment
|
| 31 |
+
|
| 32 |
+
# ai learning
|
| 33 |
+
the ai periodicaly relearns things based on your conversations and its original training data(as i mentioned, it lacks things)
|
| 34 |
+
|
| 35 |
+
# limitations
|
| 36 |
+
the ai is not perfect(no one is), just like a human, it will generate wrong information, but be patient, it is learning from its mistakes and it will eventualy be better then post production
|